© 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. 2940
    Prev
    Next
    INDEX
    Explanations

    mathematical derivatives and rates of change

    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
     чувство
    -0.82
     artesanía
    -0.81
     صنعتی
    -0.79
     ecológica
    -0.78
    RATES
    -0.77
     Funktionen
    -0.75
    兵衛
    -0.74
    bastien
    -0.73
     derivados
    -0.73
    frac
    -0.73
    POSITIVE LOGITS
     móng
    0.93
    zi
    0.77
     pleine
    0.76
    を描く
    0.74
    加拿
    0.74
    ご紹介
    0.73
    にとっては
    0.73
    を変える
    0.73
     جس
    0.73
    TIN
    0.73
    Activations Density 0.006%

    No Known Activations