© 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. 150257
    Prev
    Next
    INDEX
    Explanations

    available to you

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

    found, lost, win, shooter

    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
    ﺘ
    0.53
    टी
    0.49
    ’)
    0.48
    t
    0.46
     ALL
    0.44
    REAM
    0.44
     )
    0.43
     N
    0.43
    ')
    0.43
    应用程序
    0.43
    POSITIVE LOGITS
    verfahren
    0.50
     மிகுந்த
    0.50
     التن
    0.49
     proizvod
    0.48
    மிக
    0.48
     reconstru
    0.47
     ottenere
    0.46
     vivre
    0.46
     speciali
    0.46
     reconstruction
    0.46
    Activations Density 0.000%

    No Known Activations