© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 177863
    Prev
    Next
    INDEX
    Explanations

    trade war, powers, ailment, power, record

    np_acts-logits-general · gemini-2.5-flash-lite

    identifying common

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     数
    0.50
     為
    0.47
     ۷
    0.42
     möglichen
    0.42
     ۸
    0.41
    ۷
    0.40
     ۵
    0.40
    فت
    0.40
    Estimation
    0.39
    渐
    0.39
    POSITIVE LOGITS
     HCO
    0.50
    ilizar
    0.46
    ATORS
    0.46
    issory
    0.46
     THINGS
    0.43
     करणे
    0.43
    FBSDKInternal
    0.43
    న్లు
    0.43
    ahooks
    0.43
    も含
    0.42
    Activations Density 0.000%

    No Known Activations