© 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. 16140
    Prev
    Next
    INDEX
    Explanations

    concepts and distributions

    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
     pourcentage
    0.57
     sintomas
    0.57
    ྕ
    0.54
     meu
    0.52
     pacient
    0.52
     manifestaciones
    0.52
     stade
    0.51
     fatores
    0.50
     altres
    0.50
     çar
    0.50
    POSITIVE LOGITS
    '
    0.64
    ’
    0.59
     Implementation
    0.57
    :
    0.57
     Entertainment
    0.56
     Electronic
    0.55
     (
    0.54
    0.53
    -
    0.53
    EL
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.