© 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. 39887
    Prev
    Next
    INDEX
    Explanations

    tragic development

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

    from basic to more

    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
     Political
    0.42
     Government
    0.41
     Exchequer
    0.41
    ði
    0.40
    .
    0.40
     Deze
    0.39
    csproj
    0.39
    炒
    0.39
    IUM
    0.39
     trader
    0.39
    POSITIVE LOGITS
     pausa
    0.52
     entidad
    0.48
     आत्म
    0.47
     అన్ని
    0.47
     escenas
    0.47
     propiedades
    0.46
     entidades
    0.46
    зня
    0.46
    мония
    0.46
     devast
    0.45
    Activations Density 0.000%

    No Known Activations