© 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. 160365
    Prev
    Next
    INDEX
    Explanations

    phrases or codes after parenthesis

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

    key, affordable, path, perfectly, stop

    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
    ב
    0.63
    כ
    0.56
    לא
    0.49
    בק
    0.49
    את
    0.49
    म
    0.49
    मेरे
    0.48
    ک
    0.48
    Functions
    0.47
    नहीं
    0.47
    POSITIVE LOGITS
     Ajoutez
    0.43
     ź
    0.42
     hosszú
    0.42
     récol
    0.42
    ={$
    0.41
     justifiable
    0.41
    chtigen
    0.40
     Regardless
    0.40
    日本人
    0.40
    xls
    0.39
    Activations Density 0.000%

    No Known Activations