© 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. 24-GEMMASCOPE-2-RES-262K
    7. 11106
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

    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_24_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
    枴
    0.61
    よい
    0.57
    deux
    0.56
    buah
    0.53
    boxyl
    0.53
    不容易
    0.52
    Password
    0.51
    busca
    0.51
    ervlak
    0.51
     bookcases
    0.51
    POSITIVE LOGITS
     (
    0.68
    お
    0.62
    0.59
     জাতিসঙ্ঘ
    0.58
     т
    0.58
    л
    0.57
    ज
    0.57
     НА
    0.56
    с
    0.56
    я
    0.55
    Activations Density 0.001%

    No Known Activations