© 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. 212712
    Prev
    Next
    INDEX
    Explanations

    in preparation or in person

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

    specific or contradictory requests

    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
     наро
    0.57
     Feelings
    0.55
    𝒃
    0.50
     तत्
    0.48
     निराशा
    0.47
    𝒏
    0.46
     προς
    0.46
    izador
    0.46
     δρα
    0.45
     perasaan
    0.44
    POSITIVE LOGITS
    hag
    0.46
     asci
    0.46
    tbl
    0.45
     hame
    0.45
    鹊
    0.44
     wieku
    0.44
    رجال
    0.43
     الشيخ
    0.42
     accu
    0.42
     ]);
    0.42
    Activations Density 0.001%

    No Known Activations