© 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. 22588
    Prev
    Next
    INDEX
    Explanations

    showing or presenting information

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

    multiple versions

    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
     constantly
    0.43
    .+
    0.40
    不断的
    0.39
     difference
    0.38
    不斷
    0.38
     régler
    0.38
    PECT
    0.37
    .\\
    0.37
    Difference
    0.37
     érdekében
    0.37
    POSITIVE LOGITS
     Това
    0.43
    aların
    0.43
    the
    0.43
    琙
    0.43
     architekt
    0.42
     குரு
    0.41
    ınca
    0.41
    rard
    0.41
    ાર
    0.41
     Interiors
    0.41
    Activations Density 0.000%

    No Known Activations