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. 12-GEMMASCOPE-2-RES-262K
    4. 44752
    Prev
    Next
    INDEX
    Explanations

    visual symbol or inspection

    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
    ه
    1.05
    ো
    0.90
    μο
    0.83
    ר
    0.83
     लिखने
    0.83
    ა
    0.82
    вым
    0.81
    했습니다
    0.81
    с
    0.81
    ה
    0.80
    POSITIVE LOGITS
     intrigue
    0.82
    社會
    0.78
     acetic
    0.77
     Diageo
    0.73
     Arne
    0.71
     urine
    0.71
     analyst
    0.70
     asphalt
    0.70
     electroly
    0.69
     offender
    0.69
    Activations Density 0.001%

    No Known Activations