© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39172
    Prev
    Next
    INDEX
    Explanations

    and followed by various words

    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_22/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
    стане
    -1.32
    реш
    -1.30
    쾰
    -1.18
    ')"
    -1.16
    着的
    -1.16
     stash
    -1.14
     espoir
    -1.11
    ofthe
    -1.10
    ㅜ
    -1.09
    '/',
    -1.09
    POSITIVE LOGITS
     then
    2.69
     they
    2.33
     that
    2.23
     I
    2.13
     you
    2.06
     it
    2.03
     we
    2.00
     there
    1.77
     basically
    1.75
     when
    1.70
    Activations Density 0.003%

    No Known Activations