© 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. 10-GEMMASCOPE-RES-131K
    7. 66605
    Prev
    Next
    INDEX
    Explanations

    want, expect, hope, think

    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
     with
    -1.70
     through
    -1.70
     during
    -1.61
     вдоль
    -1.55
     before
    -1.41
     after
    -1.38
    тое
    -1.34
    What
    -1.32
     without
    -1.29
    Through
    -1.23
    POSITIVE LOGITS
    べし
    1.44
     souri
    1.29
    流石
    1.23
    こいつ
    1.20
    うーん
    1.20
     tué
    1.15
    дила
    1.14
     respecte
    1.14
     aimable
    1.13
    買った
    1.13
    Activations Density 0.039%

    No Known Activations