© 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. 9824
    Prev
    Next
    INDEX
    Explanations

    P/S value

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

    PII, P-codes, organizations, tech frameworks

    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
    𝙉
    0.42
    ﺩ
    0.39
     pruž
    0.38
     gjennom
    0.38
     Zeitschr
    0.38
     Warum
    0.38
     různých
    0.38
    钽
    0.38
    حدد
    0.37
    鳇
    0.37
    POSITIVE LOGITS
    cP
    0.43
     politics
    0.41
    P
    0.41
    е
    0.40
     PZ
    0.38
     pays
    0.38
     punches
    0.38
     P
    0.38
     p
    0.38
     well
    0.38
    Activations Density 0.300%

    No Known Activations