© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 2763
    Prev
    Next
    INDEX
    Explanations

    input tensor shapes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    :
    0.67
     via
    0.63
    .
    0.61
     -
    0.58
    0.56
     motto
    0.55
    !
    0.55
    +
    0.55
     by
    0.55
    ).
    0.54
    POSITIVE LOGITS
    妿
    0.64
     વિસ્તાર
    0.64
    ान्य
    0.62
    麽
    0.62
     不同
    0.61
     común
    0.60
     Кі
    0.60
    冋
    0.60
     Кам
    0.59
    灲
    0.59
    Activations Density 0.001%

    No Known Activations