© 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. 97720
    Prev
    Next
    INDEX
    Explanations

    generally upward

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

    generally discloses, for believers, they make

    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
     to
    0.56
     (
    0.52
     whence
    0.52
     where
    0.51
     thence
    0.51
     in
    0.50
     either
    0.48
     boasting
    0.47
     by
    0.47
     -
    0.46
    POSITIVE LOGITS
     مجموع
    0.50
     relativement
    0.49
     ভূ
    0.48
     පහ
    0.47
     ఎక్కువగా
    0.47
    敉
    0.46
    𝙙
    0.46
    MatContext
    0.46
    ologiques
    0.45
     قتل
    0.45
    Activations Density 0.001%

    No Known Activations