© 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. 228412
    Prev
    Next
    INDEX
    Explanations

    Rooms, beginning, appealing

    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
     utilisant
    0.52
    lowski
    0.52
    Ttest
    0.49
     Durchführung
    0.48
     scienza
    0.46
     따라서
    0.45
     Elektrokhimiya
    0.45
    📐
    0.45
     utilisez
    0.45
     scrittura
    0.45
    POSITIVE LOGITS
     vacation
    0.48
    -
    0.46
    have
    0.44
     passengers
    0.43
     there
    0.41
    also
    0.41
     certainly
    0.41
     soared
    0.40
     also
    0.39
    holiday
    0.39
    Activations Density 0.000%

    No Known Activations