© 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. 10-GEMMASCOPE-RES-131K
    7. 59385
    Prev
    Next
    INDEX
    Explanations

    allegations, claims, concerns, speculation

    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_10/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
     また
    -1.53
    ي
    -1.52
     喜欢
    -1.44
    なぜ
    -1.42
    未完
    -1.41
     complicada
    -1.41
    だったが
    -1.39
    ﹡
    -1.32
    注解
    -1.32
     Erfolge
    -1.32
    POSITIVE LOGITS
     that
    1.66
     you
    1.56
    再也
    1.52
    b
    1.51
    zation
    1.48
     dette
    1.45
    www
    1.44
     kollu
    1.40
    com
    1.36
    si
    1.35
    Activations Density 0.034%

    No Known Activations