© 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. 237225
    Prev
    Next
    INDEX
    Explanations

    hypnotist, international, Kit, Open

    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
    籀
    0.49
     restrained
    0.49
    ственного
    0.48
    akkhati
    0.47
    chwitz
    0.46
     éste
    0.46
     Stab
    0.45
     chave
    0.45
     tailored
    0.44
     стрелецкой
    0.44
    POSITIVE LOGITS
    NI
    0.54
    3
    0.52
    DE
    0.50
    postcard
    0.50
    thirty
    0.50
    DIC
    0.48
    application
    0.48
    minute
    0.48
    DC
    0.47
    DFT
    0.47
    Activations Density 0.001%

    No Known Activations