© 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. 11405
    Prev
    Next
    INDEX
    Explanations

    LLM AI risks and capabilities

    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
    Έ
    1.03
    oi
    1.02
    '
    1.00
     senses
    0.98
     siècles
    0.98
    ри
    0.97
    üng
    0.97
    iki
    0.96
     কলিকাতা
    0.96
    \<
    0.95
    POSITIVE LOGITS
     efectivamente
    1.10
    ﻟ
    1.02
    ラー
    0.97
    s
    0.97
    ల్
    0.95
    ン
    0.95
    களில்
    0.92
     especificar
    0.91
    و
    0.90
    น
    0.90
    Activations Density 0.185%

    No Known Activations