© 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. 30329
    Prev
    Next
    INDEX
    Explanations

    reserved rights

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    înt
    -0.79
    UNDLE
    -0.77
    打ち
    -0.76
    Destruction
    -0.76
    Deposits
    -0.76
     strict
    -0.75
    bukti
    -0.74
    ichio
    -0.74
     vueltas
    -0.73
    一身
    -0.72
    POSITIVE LOGITS
    ℳ
    0.71
    NickName
    0.71
     own
    0.71
    ený
    0.71
    getNext
    0.69
    LEIA
    0.68
    Reminder
    0.68
    hilfe
    0.68
    คง
    0.68
    Recogn
    0.66
    Activations Density 0.003%

    No Known Activations