© 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. 4159
    Prev
    Next
    INDEX
    Explanations

    it means

    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
    ת
    1.99
    ا
    1.93
    ли
    1.83
    у
    1.79
    い
    1.70
    也
    1.68
    s
    1.65
    т
    1.65
    د
    1.63
    ות
    1.63
    POSITIVE LOGITS
     pamoja
    1.84
    garten
    1.73
    ty
    1.64
    ส์
    1.50
    tting
    1.46
    daki
    1.45
    bian
    1.44
    Pourquoi
    1.43
    tai
    1.41
    greedy
    1.40
    Activations Density 0.593%

    No Known Activations