© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 346
    Prev
    Next
    INDEX
    Explanations

    python requests for APIs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_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
    DV
    1.73
     Logos
    1.70
     Deep
    1.66
    DT
    1.64
    Number
    1.64
     RSS
    1.63
     DV
    1.63
    <sub>
    1.63
     logo
    1.62
     logos
    1.60
    POSITIVE LOGITS
    挛
    0.76
     continuant
    0.58
     inquiet
    0.57
    遏
    0.56
    abhavo
    0.56
     inmate
    0.55
    เมริกา
    0.51
    ほか
    0.48
     ortam
    0.47
    不敢
    0.47
    Activations Density 1.116%

    No Known Activations