© 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. 44390
    Prev
    Next
    INDEX
    Explanations

    legal citations f.2d

    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
     Both
    -2.81
    ...
    -2.73
    。
    -2.66
    :
    -2.55
    ....
    -2.53
    0
    -2.45
    '
    -2.45
    .........
    -2.34
    —
    -2.33
    !
    -2.27
    POSITIVE LOGITS
     whom
    2.25
     belangrij
    2.19
     becoming
    2.11
     who
    2.09
    しと
    2.06
     which
    2.03
     pero
    2.02
    
    2.00
     детей
    1.96
     邸
    1.96
    Activations Density 0.170%

    No Known Activations