© 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. 128569
    Prev
    Next
    INDEX
    Explanations

    either/or choices

    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
    ுக்கு
    -1.61
     needed
    -1.38
    场比赛
    -1.36
     necessary
    -1.33
     necesitan
    -1.32
    日的
    -1.32
     necesarios
    -1.31
    不但
    -1.24
    possessed
    -1.23
     ganzes
    -1.22
    POSITIVE LOGITS
     of
    1.40
     menem
    1.30
    :
    1.27
    춤
    1.20
     this
    1.17
     ahí
    1.10
    されます
    1.09
    祥
    1.08
    TAWA
    1.06
    vière
    1.05
    Activations Density 0.087%

    No Known Activations