© 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. 68230
    Prev
    Next
    INDEX
    Explanations

    color manipulation

    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
    ってみた
    -1.82
     timmar
    -1.70
     erstes
    -1.59
    Только
    -1.54
    鉺
    -1.43
    atteindre
    -1.42
    撂
    -1.42
    躋
    -1.42
    !’
    -1.41
    ってください
    -1.41
    POSITIVE LOGITS
     of
    2.23
     that
    1.70
     --
    1.45
    的事情
    1.43
    ࿙
    1.42
     podob
    1.41
    ванием
    1.41
    涉及
    1.38
     since
    1.38
     on
    1.37
    Activations Density 0.001%

    No Known Activations