© 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. 163939
    Prev
    Next
    INDEX
    Explanations

    internet users, these cookies

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

    classes, income, factions, mappings

    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
     doel
    0.50
    ん
    0.50
     beau
    0.47
    Ray
    0.46
    时代
    0.46
     فهي
    0.46
    la
    0.45
    𝟐
    0.43
    pale
    0.43
     definido
    0.42
    POSITIVE LOGITS
     کاروبار
    0.49
     homology
    0.48
     monolithic
    0.47
     monolith
    0.47
     remembering
    0.45
     liquidated
    0.44
    ٹوں
    0.43
    ostridium
    0.43
    oluminescence
    0.43
    원본파일명
    0.43
    Activations Density 0.000%

    No Known Activations