© 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. 200320
    Prev
    Next
    INDEX
    Explanations

    explains what, shall have, look forward, advertised products

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

    dopamine, case considerations, candidature

    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
    普通の
    0.46
    Ⅺ
    0.44
    сподар
    0.42
     노동
    0.42
    ochastic
    0.42
    公式
    0.42
    accam
    0.42
    _
    0.41
     safer
    0.41
    裸
    0.41
    POSITIVE LOGITS
     tới
    0.49
    ية
    0.48
     sách
    0.46
     coûte
    0.46
     exhausts
    0.45
     hương
    0.44
     confuses
    0.44
    ెంట్
    0.43
     tastes
    0.43
     jusqu
    0.42
    Activations Density 0.000%

    No Known Activations