© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 43623
    Prev
    Next
    INDEX
    Explanations

    named or called

    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
    ي
    0.94
    Een
    0.92
     Apk
    0.87
    ség
    0.85
    ný
    0.84
    तील
    0.83
    णसी
    0.81
    ekan
    0.81
     sábado
    0.80
     plantings
    0.80
    POSITIVE LOGITS
    kosten
    0.90
    pose
    0.89
    it
    0.85
    𝘔
    0.84
     ск
    0.83
    ieť
    0.83
     thoroughly
    0.82
    cích
    0.80
    𝚄
    0.80
    ఝ
    0.79
    Activations Density 0.000%

    No Known Activations