© 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. 106934
    Prev
    Next
    INDEX
    Explanations

    get and fail

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

    implementation using

    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
    <unused1>
    0.51
    хождения
    0.48
    ли
    0.47
     атмосфер
    0.47
    अर
    0.45
    میر
    0.44
    рас
    0.43
    торы
    0.43
    י
    0.43
    риса
    0.43
    POSITIVE LOGITS
    unch
    0.53
    k
    0.52
     Sikhs
    0.52
     Fonda
    0.48
    g
    0.47
     ಮುಂದ
    0.46
     won
    0.46
     Tickets
    0.45
     hola
    0.45
     f
    0.45
    Activations Density 0.000%

    No Known Activations