© 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. 134675
    Prev
    Next
    INDEX
    Explanations

    rectangle stickers

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

    resumes, sites, coin

    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
    ای
    0.49
    داد
    0.48
    泻
    0.48
     destra
    0.45
    ರ್ಶ
    0.45
     múltipl
    0.45
     cairan
    0.44
     asociado
    0.44
     gaussian
    0.44
     ricost
    0.44
    POSITIVE LOGITS
    ptu
    0.48
    cler
    0.47
    Charlie
    0.47
     অ
    0.47
    vaa
    0.46
    ering
    0.45
     選
    0.45
    Responsive
    0.45
    ahl
    0.45
    peror
    0.44
    Activations Density 0.000%

    No Known Activations