© 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. 177554
    Prev
    Next
    INDEX
    Explanations

    If sophisticated

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

    enhancement eggs recall science refers good

    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
    🌡
    0.47
    🐡
    0.47
    쳤
    0.47
    짝
    0.46
    다면
    0.45
    옛
    0.45
    ब्राह
    0.44
    드
    0.44
    ும்போது
    0.43
    WORKS
    0.43
    POSITIVE LOGITS
     clues
    0.49
     listing
    0.47
    実際の
    0.47
     θε
    0.46
     assess
    0.46
     monsieur
    0.45
     actuality
    0.45
     pamphlets
    0.44
     catheters
    0.44
     évent
    0.43
    Activations Density 0.000%

    No Known Activations