© 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. 99594
    Prev
    Next
    INDEX
    Explanations

    a self

    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
     amount
    0.40
    0
    0.40
    rought
    0.39
     hours
    0.38
    Rome
    0.38
    9
    0.38
     nine
    0.38
     часа
    0.38
    0.38
     round
    0.37
    POSITIVE LOGITS
     advogado
    0.55
    律师
    0.48
    掮
    0.47
    生日
    0.45
    Businessman
    0.45
    对外
    0.45
    itiva
    0.44
     avocat
    0.43
    thememanager
    0.42
     belliger
    0.42
    Activations Density 0.000%

    No Known Activations