© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 8954
    Prev
    Next
    INDEX
    Explanations

    Crisis Text Line HOME to 741741

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    ahme
    1.17
     solvency
    1.17
    或
    1.14
    mediated
    1.13
     myogenic
    1.12
     вино
    1.11
    sufficiency
    1.11
     queries
    1.10
     או
    1.09
    ̵
    1.09
    POSITIVE LOGITS
    };
    1.00
                
    0.98
     finalized
    0.96
     [],
    0.96
    aruh
    0.95
     Western
    0.93
    y
    0.92
     Kennel
    0.92
     Detta
    0.92
    Western
    0.90
    Activations Density 0.036%

    No Known Activations