© 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. 177654
    Prev
    Next
    INDEX
    Explanations

    various languages and punctuation

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

    understand the

    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
    AUX
    0.49
     Endocr
    0.49
    Pda
    0.48
     অর্ধ
    0.46
    `<
    0.46
    க்கழக
    0.45
    establishment
    0.45
     Yaman
    0.45
    toISO
    0.44
    yto
    0.44
    POSITIVE LOGITS
     même
    0.55
     réponse
    0.55
    ри
    0.54
     décision
    0.52
     variável
    0.49
    ة
    0.49
     remarque
    0.48
    न
    0.48
    ن
    0.48
     directeur
    0.48
    Activations Density 0.001%

    No Known Activations