© 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. 59178
    Prev
    Next
    INDEX
    Explanations

    dumpster company, be workable, the case

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

    background color

    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
    Dealer
    0.50
    dealer
    0.43
     تصير
    0.43
    aud
    0.42
    Metadata
    0.41
    删
    0.41
     रॉबर्ट
    0.41
     희
    0.39
    桉
    0.39
    逮捕
    0.39
    POSITIVE LOGITS
     brane
    0.54
     maneras
    0.49
    ӵ
    0.49
     orada
    0.47
     kerana
    0.46
     TEMPERATURE
    0.46
    ;
    0.46
     buton
    0.45
    hjust
    0.45
    ϑ
    0.45
    Activations Density 0.000%

    No Known Activations