© 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. 72433
    Prev
    Next
    INDEX
    Explanations

    sports, hobbies, gaming, night, develop

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

    changes, stretches, managed, after

    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
    nya
    0.47
    了
    0.47
     he
    0.47
    0.45
    as
    0.44
    tib
    0.43
    ahid
    0.43
    Ａ
    0.42
    emal
    0.42
    정도
    0.41
    POSITIVE LOGITS
    candles
    0.55
     nourrir
    0.54
     transistors
    0.52
     pouches
    0.51
     হোমিওপ্যাথির
    0.51
     poudre
    0.50
     হাজারের
    0.50
     granules
    0.50
    واكب
    0.49
     boilers
    0.49
    Activations Density 0.001%

    No Known Activations