© 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. 194
    Prev
    Next
    INDEX
    Explanations

    accuracy

    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
    tiden
    2.20
    s
    1.94
    tener
    1.73
    task
    1.69
    ுக
    1.63
    odore
    1.63
    ture
    1.60
    ころ
    1.55
    ราะห์
    1.55
    تان
    1.52
    POSITIVE LOGITS
    ре
    1.88
    IW
    1.82
    𝑻
    1.68
    𝑰
    1.55
    كل
    1.52
    𝑳
    1.52
     És
    1.50
    𝐼
    1.50
    О
    1.48
    IENT
    1.45
    Activations Density 0.036%

    No Known Activations