© 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. 14664
    Prev
    Next
    INDEX
    Explanations

    value range

    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
     newer
    0.76
    7
    0.71
    6
    0.67
    4
    0.65
    8
    0.65
    ۶
    0.65
    ன்று
    0.65
     masak
    0.64
    9
    0.64
    3
    0.63
    POSITIVE LOGITS
    +",
    0.72
    ⁣⁣
    0.70
     ″
    0.69
    !”,
    0.68
     بونس
    0.65
     SOI
    0.64
    .’’
    0.64
    oproteins
    0.63
     Mose
    0.63
     」
    0.63
    Activations Density 0.045%

    No Known Activations