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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7108
    Prev
    Next
    INDEX
    Explanations

    licensed under the Apache license

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

    This neuron fires most strongly on unusually long tokens (such as multi‐word identifiers, license names, permissions, or long numeric strings).

    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
    BIA
    -0.72
     Pf
    -0.63
    صبح
    -0.63
    演
    -0.63
     stairway
    -0.63
    ያ
    -0.63
    жется
    -0.62
     nhãn
    -0.62
     MSC
    -0.62
    pms
    -0.62
    POSITIVE LOGITS
    әне
    0.77
    feas
    0.76
    rational
    0.74
     Manners
    0.73
     dangereux
    0.72
     trotz
    0.70
     escolares
    0.69
     ViewHolder
    0.69
    yellow
    0.69
    pography
    0.66
    Activations Density 0.044%

    No Known Activations