© 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. 48765
    Prev
    Next
    INDEX
    Explanations

    abe|be|obe prefixes

    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
    soe
    -0.78
     Calculation
    -0.76
    lng
    -0.72
    riers
    -0.71
    économ
    -0.71
    datei
    -0.70
    جراء
    -0.70
    อยู่ใน
    -0.69
    fördert
    -0.69
    ries
    -0.69
    POSITIVE LOGITS
    AUF
    0.93
    beho
    0.84
    emis
    0.83
    bé
    0.81
    venske
    0.81
     abe
    0.76
    bria
    0.76
    司马
    0.74
    friend
    0.73
    ucie
    0.73
    Activations Density 0.026%

    No Known Activations