© 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. 51922
    Prev
    Next
    INDEX
    Explanations

    fishing club

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

    daily ride check

    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
    Ⲕ
    0.48
    літи
    0.47
    літ
    0.46
    гти
    0.44
    єн
    0.43
    nDims
    0.43
    詞
    0.43
    쿄
    0.43
    ГО
    0.43
    Baer
    0.42
    POSITIVE LOGITS
     ¡
    0.54
     Pokémon
    0.48
    }{\
    0.47
     Polynesian
    0.47
    ^{
    0.46
     Thai
    0.46
     Pikachu
    0.45
     Jurassic
    0.45
     Joe
    0.44
     promoc
    0.44
    Activations Density 0.000%

    No Known Activations