© 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. 22-GEMMASCOPE-RES-131K
    7. 33334
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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_22/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
    zac
    -0.96
    caden
    -0.95
    tismo
    -0.92
    onymus
    -0.91
    bren
    -0.90
     Características
    -0.90
    ###########
    -0.89
    lloworld
    -0.89
    cestor
    -0.89
     week
    -0.89
    POSITIVE LOGITS
     distanza
    1.04
    9
    0.94
     キャ
    0.87
     написать
    0.86
     REPLIES
    0.86
    8
    0.85
    มีความ
    0.85
     pfle
    0.85
    5
    0.85
    G
    0.85
    Activations Density 0.001%

    No Known Activations