© 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. 80392
    Prev
    Next
    INDEX
    Explanations

    blood sugar, again learn, error learn, for that, of year, accepting that

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

    not necessarily

    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
     outage
    0.47
     견
    0.47
     отрасли
    0.47
     থামাতে
    0.45
     zabud
    0.44
     lockers
    0.43
     လုပ်
    0.43
     checkpoint
    0.43
    ಸ
    0.43
    },"
    0.43
    POSITIVE LOGITS
    ća
    0.48
    herald
    0.45
    Lex
    0.44
     Monkeys
    0.43
    ູນ
    0.42
    Genero
    0.42
    Lawrence
    0.42
     Lexington
    0.42
    iseks
    0.42
     necessari
    0.41
    Activations Density 0.001%

    No Known Activations