© 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. 255020
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    廪
    0.45
     здрав
    0.43
    лася
    0.42
    ählt
    0.42
    ኛው
    0.41
     билет
    0.41
    Cantidad
    0.41
    ventud
    0.41
     транспорти
    0.41
    setMessage
    0.40
    POSITIVE LOGITS
     prélim
    0.45
     derivatives
    0.44
     teore
    0.44
    proficiency
    0.44
    ὀ
    0.44
     few
    0.42
    ोग
    0.42
     fung
    0.42
     ano
    0.42
     flaw
    0.42
    Activations Density 0.000%

    No Known Activations