© 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. 43787
    Prev
    Next
    INDEX
    Explanations

    requesting certain things

    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
    ан
    0.59
    драв
    0.50
    ум
    0.50
     علشان
    0.49
     февраля
    0.49
    ана
    0.48
    рез
    0.48
    ５
    0.48
    аль
    0.48
    бу
    0.47
    POSITIVE LOGITS
     Latte
    0.50
     Hal
    0.50
     Butte
    0.49
     Pati
    0.49
     आले
    0.49
     Rugby
    0.48
     Aix
    0.47
     Moulin
    0.47
     Chlor
    0.47
    formul
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.