© 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. 14250
    Prev
    Next
    INDEX
    Explanations

    at

    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
     Và
    0.91
    <unused1086>
    0.90
     alcoved
    0.90
     וש
    0.88
    órico
    0.87
    ্্র
    0.87
    cbind
    0.87
    𒇫
    0.86
    <unused1219>
    0.86
    Lời
    0.85
    POSITIVE LOGITS
     at
    0.88
     we
    0.88
     its
    0.88
     just
    0.83
     every
    0.77
     roughly
    0.75
     *
    0.75
     i
    0.72
     young
    0.72
     age
    0.71
    Activations Density 0.000%

    No Known Activations