© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    XGBoost, Arangodb, San Francisco

    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
     Tit
    0.84
    태
    0.79
    Ti
    0.79
     tit
    0.77
    micro
    0.76
    Tit
    0.76
     일
    0.71
     Ti
    0.70
     hil
    0.67
    ตา
    0.65
    POSITIVE LOGITS
    σσ
    1.68
    appers
    1.56
     Ghosh
    1.53
    ack
    1.50
    azaar
    1.48
    ocks
    1.47
    acken
    1.47
    ENSOR
    1.47
    pell
    1.47
    ocken
    1.47
    Activations Density 0.186%

    No Known Activations