© 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. 154033
    Prev
    Next
    INDEX
    Explanations

    final appearance or data update

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

    latest/recent data, estimates

    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
     Detect
    0.43
    ämm
    0.43
    riebe
    0.43
     detecting
    0.42
    entrada
    0.42
    importanza
    0.42
     বেদনা
    0.42
    ڃ
    0.42
    inizio
    0.41
    ಬೇ
    0.41
    POSITIVE LOGITS
     estimés
    0.49
     карь
    0.48
    ૧
    0.47
     concierge
    0.45
     Cata
    0.45
     publiés
    0.43
     transatlantic
    0.43
     получа
    0.43
     конвер
    0.42
     boardroom
    0.42
    Activations Density 0.001%

    No Known Activations