© 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. 66527
    Prev
    Next
    INDEX
    Explanations

    variety of

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

    digit 2

    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
     satte
    0.47
     生地
    0.45
    ]=
    0.44
    latest
    0.44
    ],
    0.43
     同
    0.43
     словарь
    0.43
    ]);
    0.42
    icile
    0.42
    jednoc
    0.42
    POSITIVE LOGITS
     enhancer
    0.45
     segítség
    0.44
    嬰
    0.44
     negotiate
    0.43
    買い
    0.43
    이지만
    0.42
     advantages
    0.42
    다고
    0.42
     tents
    0.42
     godt
    0.42
    Activations Density 0.001%

    No Known Activations