© 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. 114589
    Prev
    Next
    INDEX
    Explanations

    describing state, color, or purpose

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

    introduces specific concepts or domains

    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
    4
    0.52
    激安
    0.50
    Unlocked
    0.49
    <0xDC>
    0.46
    風
    0.46
    も
    0.45
    所以
    0.44
    結婚
    0.44
    薄
    0.44
    女性
    0.44
    POSITIVE LOGITS
     Verfahren
    0.52
     Solskjaer
    0.50
     idxf
    0.49
     argc
    0.49
     maart
    0.49
     događ
    0.49
    ச்செ
    0.48
     setToDefault
    0.48
     입장
    0.48
     செய்
    0.47
    Activations Density 0.001%

    No Known Activations