© 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. 91389
    Prev
    Next
    INDEX
    Explanations

    card games, computer hardware

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

    denim skirt, deeper cleaning, Accreditation Body

    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
     verdicts
    0.51
     seizoen
    0.49
     verdict
    0.48
     bienvenidos
    0.47
     avances
    0.46
     目前
    0.45
    亘
    0.45
    је
    0.45
     звезды
    0.45
     tuttavia
    0.45
    POSITIVE LOGITS
    user
    0.49
    using
    0.47
    users
    0.46
    stationary
    0.45
     peripheral
    0.43
     Stationary
    0.43
     PC
    0.43
    shall
    0.42
    util
    0.42
    asaki
    0.42
    Activations Density 0.000%

    No Known Activations