© 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. 10-GEMMASCOPE-RES-131K
    7. 19765
    Prev
    Next
    INDEX
    Explanations

    but also

    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_10/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
     that
    -1.44
     utilizarse
    -1.38
     into
    -1.35
     podía
    -1.35
     prøve
    -1.31
    eterangan
    -1.30
     tisch
    -1.23
    裏面
    -1.22
    heiten
    -1.16
     spør
    -1.16
    POSITIVE LOGITS
    these
    1.30
     thịt
    1.17
    dijo
    1.17
     TAMBIÉN
    1.17
    RefNanny
    1.16
     schwarze
    1.16
     Sebab
    1.15
    ヤバ
    1.15
    June
    1.14
    whose
    1.14
    Activations Density 0.016%

    No Known Activations