© 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. 238656
    Prev
    Next
    INDEX
    Explanations

    time, length, contributions

    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
    ре
    0.48
    ئو
    0.47
    太郎
    0.47
     eukaryotes
    0.46
     Royaume
    0.46
    当
    0.45
     Juillet
    0.45
     CTCF
    0.45
     EQS
    0.45
    ]]).
    0.45
    POSITIVE LOGITS
    asis
    0.48
    opi
    0.47
    oce
    0.47
    even
    0.46
    ine
    0.46
    ant
    0.44
     pok
    0.44
    ies
    0.44
    ical
    0.44
    cante
    0.44
    Activations Density 0.000%

    No Known Activations