© 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. 36171
    Prev
    Next
    INDEX
    Explanations

    AUTO_INCREMENT PRIMARY KEY

    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
    as
    1.16
    y
    1.16
    々は
    1.03
    ي
    1.03
     maximizes
    1.01
    ি
    0.98
    aszt
    0.96
     optimizes
    0.94
    तीत
    0.89
    助于
    0.89
    POSITIVE LOGITS
    Rustic
    1.02
    START
    0.99
    ОВ
    0.99
    ቿ
    0.98
    ים
    0.97
    บ้าน
    0.97
    ล่าสุด
    0.96
    ات
    0.95
    Så
    0.95
    ToLower
    0.93
    Activations Density 0.000%

    No Known Activations