© 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. 238933
    Prev
    Next
    INDEX
    Explanations

    specific word followed by context

    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
     foliis
    0.56
    又は
    0.55
     jährlich
    0.54
     longues
    0.52
     ឬ
    0.50
    を用いて
    0.50
    Rw
    0.49
     präsent
    0.49
    بري
    0.49
     Luís
    0.49
    POSITIVE LOGITS
     concealment
    0.48
     covenant
    0.47
    onk
    0.47
     world
    0.46
    t
    0.46
     semiconductor
    0.45
     harmonic
    0.45
     definitions
    0.44
     slew
    0.44
     Kraft
    0.44
    Activations Density 0.000%

    No Known Activations