© 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. 63145
    Prev
    Next
    INDEX
    Explanations

    answer

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

    This neuron lights up on extremely high‐frequency, common function words (e.g. “the,” “you,” “and”) regardless of context.

    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
    íteni
    -0.85
    adem
    -0.79
     elseif
    -0.79
    focusable
    -0.77
    rítica
    -0.77
    žky
    -0.77
    CESO
    -0.76
    бах
    -0.76
    idió
    -0.72
    مرار
    -0.72
    POSITIVE LOGITS
     answer
    9.06
     answers
    7.78
    answer
    6.97
     answered
    6.91
    Answer
    6.81
     answering
    6.63
     Answer
    6.50
    回答
    5.53
    answers
    5.50
     ANSWER
    5.44
    Activations Density 0.503%

    No Known Activations