© 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. 17996
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    ający
    0.48
    ộc
    0.45
    **(
    0.43
    ≐
    0.43
    ্যান্ড
    0.43
     arrivé
    0.42
    jhelp
    0.42
     ။
    0.42
    
    0.41
     লেখ
    0.41
    POSITIVE LOGITS
     http
    0.46
     سته
    0.45
     four
    0.41
     theses
    0.40
     ۴
    0.39
     hardworking
    0.39
     Considering
    0.38
     consideration
    0.38
     mini
    0.38
     www
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.