© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26303
    Prev
    Next
    INDEX
    Explanations

    meta tags, charset, viewport

    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
    ของ
    -1.20
     who
    -1.16
     zprá
    -1.14
    ACIONAL
    -1.14
    lijken
    -1.09
    CURLOPT
    -1.09
    warzys
    -1.04
    ꦶ
    -1.03
    važ
    -1.03
    ındaki
    -1.02
    POSITIVE LOGITS
    －－－－
    1.23
    AfterViewInit
    1.18
     pretože
    1.17
    porque
    1.12
     protože
    1.10
    様な
    1.08
    為に
    1.08
    뭘
    1.03
     praktisch
    1.01
     yüzden
    1.00
    Activations Density 0.015%

    No Known Activations