© 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-65K
    7. 4639
    Prev
    Next
    INDEX
    Explanations

    tournament

    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_65k_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
    筵
    1.97
     adjournment
    1.64
    insula
    1.52
     thefe
    1.45
    帷
    1.45
     stockings
    1.42
    ipennis
    1.39
     verlie
    1.39
     어떻
    1.39
    gates
    1.38
    POSITIVE LOGITS
    7
    1.47
     random
    1.34
    copy
    1.32
     execute
    1.31
     ambient
    1.31
     Rayleigh
    1.29
     jay
    1.29
     jord
    1.28
    rinsic
    1.27
    創建
    1.27
    Activations Density 0.027%

    No Known Activations