© 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. 10-GEMMASCOPE-RES-131K
    7. 44239
    Prev
    Next
    INDEX
    Explanations

    there is/has much

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

    The neuron is a high‐frequency detector—it lights up on very common “stop” words (e.g. I, is, there, much, to, no).

    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
    ༵
    -2.03
    ......”
    -1.92
    ”？
    -1.86
    𓋼
    -1.66
    ”（
    -1.64
     agujero
    -1.59
    鷓
    -1.58
    𖧵
    -1.56
     cráneo
    -1.56
    肫
    -1.55
    POSITIVE LOGITS
     Of
    2.25
    2.03
     But
    1.88
    “
    1.82
     It
    1.73
    It
    1.65
    ματα
    1.64
     Verhalten
    1.62
     Then
    1.60
    ’
    1.59
    Activations Density 0.024%
    No Known Activations