© 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. 57852
    Prev
    Next
    INDEX
    Explanations

    technical terms and code

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

    The neuron fires on key tasting‐note nouns (like “tannins,” “spice,” “flavours,” “aftertaste”) in wine reviews.

    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
    ꒥
    -0.71
    inset
    -0.71
     коса
    -0.69
     Calm
    -0.69
    Companies
    -0.68
     Companies
    -0.68
    appeal
    -0.68
     Mule
    -0.67
     Viktor
    -0.66
     aşağı
    -0.65
    POSITIVE LOGITS
    beza
    0.69
    ąp
    0.67
    fps
    0.67
    FLIP
    0.67
     得到
    0.66
    机会
    0.66
    淳
    0.65
     Clue
    0.64
    oxo
    0.64
    CMS
    0.63
    Activations Density 0.040%

    No Known Activations