© 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. 3705
    Prev
    Next
    INDEX
    Explanations

    int and integers

    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
    い
    2.06
    데
    1.73
    其他
    1.66
    มีการ
    1.63
     emeritus
    1.60
    keiten
    1.58
     evitare
    1.58
     essere
    1.55
    ii
    1.52
    jší
    1.52
    POSITIVE LOGITS
     пределах
    1.84
    ー
    1.84
    tól
    1.79
    та
    1.77
    ت
    1.73
    tener
    1.73
    ू
    1.73
    িক
    1.70
    वण
    1.70
     únicos
    1.67
    Activations Density 0.236%

    No Known Activations