© 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. 124661
    Prev
    Next
    INDEX
    Explanations

    modem card, taken advantage, combined with

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

    erotic activity or booth seating

    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
    haw
    0.49
    Url
    0.48
    Straße
    0.47
    就需要
    0.46
    E
    0.46
    pril
    0.45
    Kurt
    0.45
    StringUtils
    0.45
    Salir
    0.45
    opard
    0.44
    POSITIVE LOGITS
     dựa
    0.51
     envolvendo
    0.47
     bổ
    0.46
    ଘ
    0.46
     vibhav
    0.45
     Conventional
    0.44
     hợp
    0.43
    n
    0.43
     vải
    0.43
     savait
    0.43
    Activations Density 0.001%

    No Known Activations