© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 10014
    Prev
    Next
    INDEX
    Explanations

    technical domain keywords

    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
    وط
    0.60
    मील
    0.56
    ।
    0.53
    ียง
    0.53
    !।
    0.52
    ე
    0.49
     Cộng
    0.49
    -#
    0.48
    lh
    0.48
    يفي
    0.48
    POSITIVE LOGITS
     extravaganza
    0.68
    指的是
    0.67
     initi
    0.65
     mannequin
    0.63
    占比
    0.63
    之所以
    0.61
     alleviation
    0.61
     aspekt
    0.60
     methodologies
    0.59
     fetish
    0.59
    Activations Density 0.003%

    No Known Activations