© 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. 40127
    Prev
    Next
    INDEX
    Explanations

    semiconducting to metal

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

    associative thinking after demonstrate/again

    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
     occasioned
    0.44
    溌
    0.42
    "#
    0.41
     ஆ
    0.39
    美好的
    0.39
    φων
    0.39
    特定の
    0.39
    oplus
    0.38
     complainant
    0.38
     딸
    0.38
    POSITIVE LOGITS
     स्किल
    0.55
     organizacional
    0.53
     HMAC
    0.50
     ekonomik
    0.49
     maniak
    0.48
     bør
    0.48
     Ninh
    0.48
     Một
    0.47
     स्कि
    0.47
     Kanban
    0.47
    Activations Density 0.000%

    No Known Activations