© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 111464
    Prev
    Next
    INDEX
    Explanations

    SQL character type definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    错
    0.37
    pageY
    0.37
     આવ
    0.37
    StackTrace
    0.37
    仳
    0.36
    穰
    0.36
    డీ
    0.36
    гото
    0.36
    രിച്ചി
    0.35
    toInt
    0.35
    POSITIVE LOGITS
     varying
    0.52
     fixed
    0.48
     Vary
    0.43
    varying
    0.42
     Fixed
    0.42
    ledu
    0.40
     FIXED
    0.38
    hau
    0.37
     問
    0.37
    IMENTO
    0.37
    Activations Density 0.005%

    No Known Activations