© 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. 173127
    Prev
    Next
    INDEX
    Explanations

    ensure, race, every, Colour, day, Good, facebook

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

    programming, math, and lists

    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
     tarea
    0.50
    盡
    0.48
    FBSDKLogin
    0.48
     avanzando
    0.47
    Tarea
    0.46
     caminando
    0.46
     janela
    0.46
     Trên
    0.46
    ᾽
    0.46
     aeropuerto
    0.46
    POSITIVE LOGITS
     flourishes
    0.52
     geprüft
    0.43
     তুলেছে
    0.43
     mil
    0.42
    tested
    0.42
    rd
    0.41
    рад
    0.40
     thú
    0.40
    mil
    0.40
     poses
    0.40
    Activations Density 0.000%

    No Known Activations