© 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. 31-GEMMASCOPE-2-RES-262K
    7. 112978
    Prev
    Next
    INDEX
    Explanations

    subsequent reversals, return df, standard values

    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
     QPushButton
    0.47
    㸸
    0.47
    ңуз
    0.45
     ਅਤੇ
    0.45
    潙
    0.44
    棻
    0.44
    乨
    0.44
     Vikram
    0.43
     Jenny
    0.43
    篪
    0.42
    POSITIVE LOGITS
    '
    0.48
     godzin
    0.46
     г
    0.45
     автоматы
    0.44
     droit
    0.44
    worldwide
    0.44
     worldwide
    0.43
     гр
    0.43
     seznam
    0.43
    k
    0.43
    Activations Density 0.001%

    No Known Activations