Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 4683
    Prev
    Next
    INDEX
    Explanations

    for example or itself

    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
     the
    0.90
     this
    0.71
     where
    0.68
     a
    0.67
     because
    0.66
     using
    0.65
     letting
    0.63
     clockwise
    0.63
     regardless
    0.62
    .
    0.62
    POSITIVE LOGITS
     has
    1.24
     can
    1.03
    has
    1.03
     could
    0.98
     cannot
    0.98
     may
    0.96
     heeft
    0.93
    could
    0.92
    cannot
    0.91
     will
    0.90
    Activations Density 0.006%

    No Known Activations