© 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. 66331
    Prev
    Next
    INDEX
    Explanations

    used with SELV

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

    fft, useless, kindergarten, low

    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
    ס
    0.55
    Perfil
    0.54
    Pel
    0.52
    سام
    0.51
    Sam
    0.51
    Cats
    0.51
    די
    0.50
    Jug
    0.50
    سي
    0.49
    maktadır
    0.49
    POSITIVE LOGITS
     ду
    0.48
     гор
    0.48
    onDidChange
    0.47
     разу
    0.46
    缆
    0.45
     пут
    0.45
     кон
    0.44
     translational
    0.44
     вну
    0.44
     пов
    0.44
    Activations Density 0.000%

    No Known Activations