© 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. 22-GEMMASCOPE-2-RES-262K
    7. 6095
    Prev
    Next
    INDEX
    Explanations

    crime, missing

    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_22_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
     Also
    1.02
    also
    1.02
    但也
    0.97
    <h4>
    0.97
     当然
    0.96
    <h3>
    0.95
     但是
    0.95
     moreover
    0.94
    但
    0.94
     Tetapi
    0.93
    POSITIVE LOGITS
     opportunity
    0.77
     Tuesday
    0.73
     ongoing
    0.72
     occasione
    0.71
     Opportunity
    0.71
     November
    0.71
     प्रिया
    0.69
     wake
    0.69
     Mondays
    0.69
     lendemain
    0.68
    Activations Density 0.000%

    No Known Activations