© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85847
    Prev
    Next
    INDEX
    Explanations

    descriptive appraisals

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

    The neuron fires on standout capitalized words—especially adjectives—used in titles or proper names of works.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    >
    -2.72
     самая
    -2.19
     '
    -2.16
    \"
    -2.06
     devastation
    -2.03
     notre
    -2.03
    ')
    -2.03
    怍
    -2.02
     самых
    -2.02
    ↵↵
    -2.00
    POSITIVE LOGITS
    what
    2.84
    .
    2.81
    䊏
    2.48
    䊉
    2.34
    That
    2.31
    Both
    2.30
    Very
    2.22
     stile
    2.13
     Been
    2.13
    They
    2.13
    Activations Density 0.057%

    No Known Activations