© 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. 120069
    Prev
    Next
    INDEX
    Explanations

    insurance, information, solutions

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

    games in Europe

    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
    vollen
    0.46
    ovým
    0.45
    ländischen
    0.45
    teryx
    0.44
    ált
    0.44
    pä
    0.44
    ੂ
    0.44
    deckung
    0.43
    নীতিক
    0.43
     Australien
    0.43
    POSITIVE LOGITS
    )?,
    0.48
     revocation
    0.46
     lc
    0.43
     повре
    0.42
    CONCEPT
    0.42
     অনিবার
    0.42
     CONCEPT
    0.42
    angent
    0.42
     понимают
    0.42
    :',
    0.41
    Activations Density 0.000%

    No Known Activations