© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 181
    Prev
    Next
    INDEX
    Explanations

    candidate or issue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.47
     diy
    -0.97
     oportun
    -0.96
    >−</
    -0.93
    </h2>
    -0.93
    ">(</
    -0.92
    мся
    -0.91
    vitational
    -0.90
     susceptibles
    -0.89
     HttpNotFound
    -0.89
    POSITIVE LOGITS
    ⎧
    1.12
    ～～～～
    1.05
     kän
    1.04
     gjelder
    1.03
     τῶν
    1.00
    toss
    1.00
    encre
    0.99
     ficou
    0.98
     メニュー
    0.96
     WALTZ
    0.96
    Activations Density 0.049%

    No Known Activations