© 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. 36255
    Prev
    Next
    INDEX
    Explanations

    servings of 5

    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
    𝟬
    1.44
    ob
    1.41
    č
    1.40
    ş
    1.33
     և
    1.29
    ㌔
    1.23
    𝒄
    1.23
    ण्ट
    1.22
    ć
    1.21
    ឬ
    1.21
    POSITIVE LOGITS
    ल
    1.30
    ional
    1.24
    ্যের
    1.21
    ERS
    1.20
     ידי
    1.16
    sion
    1.15
    ל
    1.15
     ongles
    1.13
     בז
    1.13
    अमेरिका
    1.11
    Activations Density 0.001%

    No Known Activations