© 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. 107150
    Prev
    Next
    INDEX
    Explanations

    heritage centre

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

    less literal / more artistic

    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
    со
    0.50
    凹
    0.49
    ле
    0.48
    ζο
    0.47
    一名
    0.46
    пол
    0.45
    荊
    0.45
    ivating
    0.45
    పై
    0.44
     híbr
    0.44
    POSITIVE LOGITS
     frisch
    0.50
     appr
    0.48
     sve
    0.47
     aż
    0.47
     ritual
    0.47
     পরম
    0.46
     refresh
    0.46
     remon
    0.46
    totalSupply
    0.46
     &\
    0.45
    Activations Density 0.000%

    No Known Activations