© 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. 175727
    Prev
    Next
    INDEX
    Explanations

    various types; your vote; presentation dinner

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

    large language models and permits

    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
     stunt
    0.47
     kaliteli
    0.47
    MathMarks
    0.45
     ម
    0.44
     thuis
    0.43
     Daha
    0.43
     gece
    0.43
    缕
    0.42
    ظيم
    0.42
     tahan
    0.42
    POSITIVE LOGITS
     ಆಹಾರ
    0.46
     on
    0.45
    鋏
    0.45
     totalled
    0.45
    れない
    0.45
    перь
    0.45
     வேளாண்
    0.45
    zeich
    0.44
    BIUM
    0.44
    wm
    0.44
    Activations Density 0.001%

    No Known Activations