© 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. 7958
    Prev
    Next
    INDEX
    Explanations

    css properties

    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
     musculaire
    0.57
    ARAJYA
    0.57
     COMPLEXES
    0.55
    Acetic
    0.54
     detd
    0.54
     muque
    0.54
    𒅁
    0.53
    𒈾
    0.53
     vaginale
    0.52
     protéines
    0.52
    POSITIVE LOGITS
    background
    0.95
    font
    0.93
     font
    0.92
     background
    0.90
    margin
    0.85
    display
    0.84
     padding
    0.84
    padding
    0.84
     display
    0.83
    border
    0.83
    Activations Density 0.046%

    No Known Activations