© 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. 12-GEMMASCOPE-2-RES-262K
    7. 44433
    Prev
    Next
    INDEX
    Explanations

    most / highest / biggest

    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_12_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
    м
    2.95
    ת
    2.83
    م
    2.66
    ли
    2.59
    ки
    2.53
    al
    2.39
    י
    2.39
    e
    2.31
    ं
    2.28
    a
    2.27
    POSITIVE LOGITS
    I
    2.09
     britannique
    1.76
    }])
    1.75
    U
    1.75
    ባድ
    1.73
    },{
    1.71
     récemment
    1.66
    $)$.
    1.65
     chương
    1.63
     jelas
    1.62
    Activations Density 0.012%

    No Known Activations