© 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. 62367
    Prev
    Next
    INDEX
    Explanations

    what should you know

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

    connecting elements or workflows

    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
     রপ্ত
    0.54
    Triangle
    0.52
     PURCH
    0.50
    များကို
    0.48
     শৃঙ্খলা
    0.48
     періо
    0.46
     주기
    0.46
    꽈
    0.46
     Grundstück
    0.45
     capas
    0.45
    POSITIVE LOGITS
    tir
    0.47
     symphony
    0.45
     taxpayer
    0.44
     diminutive
    0.44
     Ross
    0.42
     retin
    0.42
     recal
    0.42
     Godwin
    0.42
     Parliament
    0.42
     validated
    0.42
    Activations Density 0.000%

    No Known Activations