© 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. 210901
    Prev
    Next
    INDEX
    Explanations

    Danielle Hunter, Savage Mountain

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

    technical processes and terms

    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
    國
    0.49
    국
    0.48
    SR
    0.46
    år
    0.45
    ן
    0.43
     hton
    0.42
    德
    0.42
     통해서
    0.41
    인
    0.41
     bertahan
    0.41
    POSITIVE LOGITS
    ⏭
    0.49
     cataly
    0.48
     dieron
    0.47
     δικ
    0.47
     жителей
    0.46
    боли
    0.45
     trá
    0.45
    ണിക്ക
    0.45
    ्रेडिट
    0.45
    👫
    0.44
    Activations Density 0.000%

    No Known Activations