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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 40678
    Prev
    Next
    INDEX
    Explanations

    fiction stories

    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
    ्स
    2.88
    ನಲ್ಲಿ
    2.38
    ਆਂ
    2.13
    ನ
    2.09
    ა
    2.08
    垍
    1.91
    ร
    1.90
    ্প
    1.85
    ️⃣
    1.84
    𝗕
    1.83
    POSITIVE LOGITS
    od
    2.05
    on
    1.99
    is
    1.94
    ad
    1.94
    ва
    1.87
    ah
    1.84
    ok
    1.77
    it
    1.73
    ally
    1.72
    ij
    1.70
    Activations Density 0.011%

    No Known Activations