© 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. 840
    Prev
    Next
    INDEX
    Explanations

    contrast with other options

    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
     <=>
    0.71
     %+
    0.69
    ూ
    0.68
    ود
    0.68
     ∈
    0.67
     Lexikon
    0.67
     Erfahr
    0.66
    的生活
    0.66
     izgub
    0.66
    腓
    0.66
    POSITIVE LOGITS
     reduc
    0.84
    ר
    0.82
    ла
    0.79
     pareja
    0.77
    কো
    0.75
    lance
    0.75
     grafico
    0.75
    ماش
    0.74
    出色
    0.74
    Iron
    0.73
    Activations Density 0.000%

    No Known Activations