© 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. 7356
    Prev
    Next
    INDEX
    Explanations

    facilitates outcomes

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

    shows purpose and effect

    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
    $.
    0.21
    \
    0.19
    '.
    0.19
    .\
    0.19
    ".
    0.18
    एन
    0.18
    ទេ។
    0.18
    ².
    0.18
    !।
    0.18
     kursi
    0.18
    POSITIVE LOGITS
     ensures
    0.37
     demonstrates
    0.35
     makes
    0.35
     gives
    0.33
     allows
    0.33
     позволяет
    0.32
     khiến
    0.32
     enables
    0.32
     exemplifies
    0.31
     позволяют
    0.31
    Activations Density 0.744%

    No Known Activations