© 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. 44435
    Prev
    Next
    INDEX
    Explanations

    followed by specific token

    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
    in
    -2.42
    on
    -2.41
    H
    -2.36
    X
    -2.14
     propias
    -2.05
    V
    -1.96
    E
    -1.91
    O
    -1.88
    D
    -1.84
     предприятия
    -1.83
    POSITIVE LOGITS
    髕
    2.70
     valentín
    2.28
     TÉCNICA
    2.27
    ࿙
    2.27
    噲
    2.20
     concorda
    2.19
    驁
    2.17
    洐
    2.17
    ಱ
    2.13
     FEBR
    2.09
    Activations Density 0.001%

    No Known Activations