© 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. 7608
    Prev
    Next
    INDEX
    Explanations

    specific names and entities

    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
     mant
    0.46
     ο
    0.44
     be
    0.43
     간
    0.43
     sus
    0.43
     조
    0.42
     ку
    0.41
     τα
    0.41
     τ
    0.40
     خ
    0.40
    POSITIVE LOGITS
    anthemum
    0.61
    issippi
    0.60
    orghini
    0.60
    👹
    0.59
    espace
    0.59
    ipedia
    0.58
    urian
    0.58
    celona
    0.57
    kirche
    0.57
     Lanka
    0.57
    Activations Density 0.315%

    No Known Activations