© 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. 84647
    Prev
    Next
    INDEX
    Explanations

    lot and block numbers

    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
     نثر
    0.43
     زمین
    0.40
     terreno
    0.39
    holy
    0.38
     restricciones
    0.38
    ->"
    0.38
    >')
    0.37
    არის
    0.37
     terrains
    0.37
     terrain
    0.36
    POSITIVE LOGITS
     Block
    0.95
    Block
    0.95
     block
    0.93
     ब्लॉक
    0.88
     blocks
    0.87
     BLOCK
    0.86
    块
    0.86
     Blocks
    0.85
    block
    0.83
     parcel
    0.82
    Activations Density 0.005%

    No Known Activations