© 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. 601
    Prev
    Next
    INDEX
    Explanations

    Mirror on, block ., Starbucks ., file ,, *, 4, ppled if, see with, integrated on, Go later

    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
     szüks
    0.44
    ➘
    0.43
     incisions
    0.42
     HAVING
    0.42
    jokes
    0.41
    ウド
    0.41
    িকর
    0.40
    かを
    0.40
    
    0.40
     colaborar
    0.40
    POSITIVE LOGITS
    in
    0.47
     Studien
    0.45
    av
    0.44
     Br
    0.44
     presented
    0.43
    im
    0.43
     nonlinear
    0.43
     Herrmann
    0.43
    ähn
    0.42
     Etienne
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.