© 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. 242076
    Prev
    Next
    INDEX
    Explanations

    accusing, came, deserve, dive, playing

    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
     効果
    0.55
    ANG
    0.54
     容量
    0.52
     完成
    0.49
    椀
    0.49
     এজন্য
    0.48
     場
    0.48
     أع
    0.48
     สำหรับ
    0.48
    NOT
    0.47
    POSITIVE LOGITS
     kinetic
    0.54
     martial
    0.51
     rule
    0.50
     computer
    0.50
     scribe
    0.50
     tincture
    0.49
     horror
    0.49
     monarchy
    0.49
     trial
    0.48
    ρθ
    0.47
    Activations Density 0.000%

    No Known Activations