© 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. 4490
    Prev
    Next
    INDEX
    Explanations

    not just... but

    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
     an
    0.77
     blister
    0.76
     a
    0.72
    .
    0.71
    ),
    0.70
    های
    0.68
     globular
    0.68
     fractured
    0.67
     faded
    0.67
     cleaved
    0.66
    POSITIVE LOGITS
     But
    1.37
    但不
    1.27
     αλλά
    1.23
     ngunit
    1.23
     ஆனால்
    1.20
     but
    1.18
    কিন্তু
    1.18
     কিন্তু
    1.14
    但
    1.10
    but
    1.09
    Activations Density 0.002%

    No Known Activations