© 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. 128318
    Prev
    Next
    INDEX
    Explanations

    like me or you

    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
     something
    -1.74
     olisi
    -1.61
     arī
    -1.57
    йом
    -1.47
     тоже
    -1.42
     jūs
    -1.35
     though
    -1.34
     også
    -1.32
    痿
    -1.31
     would
    -1.30
    POSITIVE LOGITS
     the
    1.35
     to
    1.34
     ambivalent
    1.23
     sommige
    1.20
     لئے
    1.20
    सार
    1.19
    หรือ
    1.18
    🦮
    1.16
    しばらく
    1.16
    celana
    1.13
    Activations Density 0.034%

    No Known Activations