© 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. 146253
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation or separators

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

    describing tasks and opinions

    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
     oneness
    0.45
     responsabilità
    0.42
     रजिस्ट
    0.41
     राह
    0.40
     є
    0.40
     kontek
    0.40
     بيانات
    0.40
     kontroll
    0.39
     MEMBERS
    0.39
     Sonos
    0.39
    POSITIVE LOGITS
     Nouveau
    0.54
     μεγά
    0.49
    iť
    0.47
     기념
    0.46
    iteurs
    0.45
    ψη
    0.44
    初回
    0.43
     agricole
    0.43
    
    0.43
    蜉
    0.42
    Activations Density 0.001%

    No Known Activations