Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84990
    Prev
    Next
    INDEX
    Explanations

    registry key, stage regression, instrumental convergence

    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_31_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
     habitually
    0.42
    IBLE
    0.41
    しくは
    0.41
     perceived
    0.40
     স্কোর
    0.40
    ド
    0.40
     пусты
    0.40
     कामयाबी
    0.40
    measurable
    0.40
     удалить
    0.39
    POSITIVE LOGITS
    Y
    0.54
     mid
    0.50
    ei
    0.50
    as
    0.48
    та
    0.47
     July
    0.47
     Angleterre
    0.47
     terme
    0.47
    ay
    0.46
     SNC
    0.46
    Activations Density 0.001%

    No Known Activations