© 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. 45840
    Prev
    Next
    INDEX
    Explanations

    as well as

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

    comparing duality or binary states

    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
     sparkly
    0.46
    방
    0.42
     वरना
    0.40
    たっぷ
    0.39
     рӯ
    0.39
     tiered
    0.38
     sparkles
    0.38
     screenings
    0.38
    房
    0.38
     fade
    0.38
    POSITIVE LOGITS
     уже
    0.55
     செயலா
    0.47
     już
    0.45
     already
    0.45
     অনুমতি
    0.44
     अत्यंत
    0.43
    éder
    0.43
     ऑलरेडी
    0.43
     ActiveX
    0.43
     ஆண
    0.42
    Activations Density 0.000%

    No Known Activations