© 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. 8198
    Prev
    Next
    INDEX
    Explanations

    environment variables or code keywords

    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
     மற்றும்
    0.86
     and
    0.79
     અને
    0.71
     almış
    0.70
    I
    0.70
    es
    0.69
     autour
    0.69
     erano
    0.68
    ındaki
    0.68
     aveva
    0.68
    POSITIVE LOGITS
     a
    1.06
     an
    1.02
     the
    0.84
    বিধা
    0.64
     а
    0.64
     Maximum
    0.64
    হোক
    0.63
     самостоя
    0.63
     Перейти
    0.63
     Crunchy
    0.63
    Activations Density 0.008%

    No Known Activations