© 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. 99830
    Prev
    Next
    INDEX
    Explanations

    arm joints and parts

    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
    鹮
    -2.44
     “
    -2.36
     mesmer
    -2.34
    錾
    -2.31
    尛
    -2.30
     cadeiras
    -2.19
    いかがでしょうか
    -2.08
    which
    -2.06
     дети
    -2.05
    のほうが
    -2.03
    POSITIVE LOGITS
    ↵↵
    3.06
    翃
    2.53
    ra
    2.53
    珵
    2.50
    k
    2.48
    h
    2.41
    ᐠ
    2.34
    ه
    2.27
    m
    2.27
    чности
    2.27
    Activations Density 0.010%

    No Known Activations