© 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. 57895
    Prev
    Next
    INDEX
    Explanations

    serviced by Rolex

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

    optimize performance

    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
     possiamo
    0.51
     getWeather
    0.50
    ણને
    0.47
     mogą
    0.47
    Puedes
    0.46
     μπορούν
    0.45
     whenever
    0.44
    <unused410>
    0.44
     jeśli
    0.44
     everytime
    0.44
    POSITIVE LOGITS
     &
    0.55
     および
    0.51
    financing
    0.50
     및
    0.50
     සහ
    0.49
    銷售
    0.49
     financing
    0.49
     及
    0.48
     shareholder
    0.47
     மற்றும்
    0.47
    Activations Density 0.000%

    No Known Activations