© 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. 9628
    Prev
    Next
    INDEX
    Explanations

    sum partition

    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
    towe
    -0.91
    НОВ
    -0.91
    eep
    -0.88
    critti
    -0.87
    dAtA
    -0.86
    Ῥ
    -0.86
    hecimento
    -0.85
     peintures
    -0.85
     geschenk
    -0.84
    AHUL
    -0.84
    POSITIVE LOGITS
     rozwiązania
    0.97
     goal
    0.96
     from
    0.94
     with
    0.94
     akzeptieren
    0.93
    зию
    0.93
     created
    0.91
     finances
    0.91
     possible
    0.91
     soste
    0.91
    Activations Density 0.009%

    No Known Activations