© 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. 98978
    Prev
    Next
    INDEX
    Explanations

    `__init__` method

    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
     seeds
    0.40
    wch
    0.39
    灑
    0.38
     ($_
    0.37
     seed
    0.37
    くる
    0.37
    মেজ
    0.36
    僳
    0.36
     Among
    0.36
     among
    0.35
    POSITIVE LOGITS
    self
    0.44
    émi
    0.44
    Lit
    0.41
    oda
    0.39
     self
    0.39
    oger
    0.38
    Instruction
    0.38
    ellan
    0.37
    SELF
    0.37
     Fore
    0.36
    Activations Density 0.001%

    No Known Activations