© 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. 32738
    Prev
    Next
    INDEX
    Explanations

    end justifications, results, user, markets, nigh

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

    end-to-end

    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
    0.57
    '
    0.55
     ০১
    0.54
    0.53
    <tr>
    0.52
     birinci
    0.51
    0.50
    €™
    0.49
     বেরিয়ে
    0.49
     বেরিয়ে
    0.49
    POSITIVE LOGITS
     end
    1.24
    end
    1.10
    端
    1.03
    端的
    1.02
    ToEnd
    0.99
     End
    0.96
     концов
    0.96
    End
    0.94
     конец
    0.89
     кін
    0.84
    Activations Density 0.046%

    No Known Activations