© 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. 97785
    Prev
    Next
    INDEX
    Explanations

    Android apps, Airline rating, security

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

    features, PB, customize

    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
    Pokud
    0.46
     Goog
    0.45
    Creo
    0.45
     Powers
    0.44
     Ciencia
    0.44
    PerTrial
    0.44
    仑
    0.44
    瑀
    0.43
     reimag
    0.43
     dacă
    0.42
    POSITIVE LOGITS
    constr
    0.46
    caption
    0.45
     своей
    0.43
    ᱙
    0.43
     название
    0.43
     envisaged
    0.42
    franch
    0.42
    MATRIX
    0.41
    clazz
    0.41
     배경
    0.40
    Activations Density 0.001%

    No Known Activations