© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 98903
    Prev
    Next
    INDEX
    Explanations

    super followed by delimiter

    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
     سلطان
    0.39
    सेप्शन
    0.39
    菊
    0.39
     científica
    0.38
    ݢ
    0.38
     Harwell
    0.38
    দি
    0.37
    utilizzo
    0.37
     የመ
    0.37
     Mak
    0.37
    POSITIVE LOGITS
    me
    0.41
     excessively
    0.38
    mole
    0.38
    Containers
    0.38
    olus
    0.37
    ime
    0.37
    Philosophy
    0.37
    ily
    0.37
     酸
    0.37
    Panel
    0.36
    Activations Density 0.000%

    No Known Activations