© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63061
    Prev
    Next
    INDEX
    Explanations

    Spinal Tap and characterization

    np_acts-logits-general · gemini-2.5-flash-lite

    popular cultural references and branded slogans.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on title-style or headline words and other capitalized proper names, i.e. it detects names and titles in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     */
    -0.84
    NextToken
    -0.75
    }}$.
    -0.74
    Delight
    -0.73
    hape
    -0.73
    ﺤ
    -0.69
    ֶׁ
    -0.69
     Gram
    -0.69
     Matters
    -0.68
     LPS
    -0.67
    POSITIVE LOGITS
     Zool
    1.37
     Anchor
    1.10
    Anchor
    1.05
     Ferrell
    0.95
     anchor
    0.81
    maha
    0.75
     tribunals
    0.74
     сайт
    0.73
    haq
    0.72
    anchor
    0.72
    Activations Density 0.015%

    No Known Activations