© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54342
    Prev
    Next
    INDEX
    Explanations

    your game / check out / slip knot

    np_acts-logits-general · gemini-2.5-flash-lite

    language and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ud
    0.51
    égi
    0.49
    sk
    0.49
    िटी
    0.47
    zk
    0.47
    sn
    0.46
    qt
    0.46
    ᱥ
    0.45
    config
    0.45
    ms
    0.44
    POSITIVE LOGITS
    欲望
    0.53
     STRONG
    0.50
     AVAILABLE
    0.49
     الاستفهام
    0.49
    졌
    0.48
     avven
    0.48
     normalen
    0.48
    ANCES
    0.48
     QUALITY
    0.48
     Pryor
    0.47
    Activations Density 0.000%

    No Known Activations