© 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. 38966
    Prev
    Next
    INDEX
    Explanations

    working with others

    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
    -1.68
     to
    -1.52
     bestimmten
    -1.41
     into
    -1.35
     однако
    -1.26
     häufiger
    -1.25
     bedeut
    -1.25
     höhere
    -1.22
     on
    -1.20
     possível
    -1.20
    POSITIVE LOGITS
    0
    1.53
    眼睛
    1.45
    ফ
    1.41
     behe
    1.39
    tell
    1.36
    èce
    1.32
     enam
    1.30
    he
    1.26
    мата
    1.24
     アン
    1.23
    Activations Density 0.014%

    No Known Activations