© 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. 41174
    Prev
    Next
    INDEX
    Explanations

    time of writing

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

    till date

    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
    ه
    0.49
    叒
    0.45
     crippling
    0.45
    هی
    0.43
    บค้น
    0.43
    чә
    0.43
     výbě
    0.42
     modulating
    0.42
    δή
    0.42
    ǽ
    0.42
    POSITIVE LOGITS
     estar
    0.55
     olsun
    0.53
    PUT
    0.52
     serem
    0.50
    UZ
    0.49
     empezar
    0.49
     iskust
    0.48
     começar
    0.45
    MMM
    0.45
    RES
    0.45
    Activations Density 0.000%

    No Known Activations