© 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. 113434
    Prev
    Next
    INDEX
    Explanations

    flying

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

    categories or specific details

    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
     data
    0.53
    TG
    0.53
     P
    0.53
     key
    0.52
     GR
    0.52
    key
    0.51
    </blockquote>
    0.50
     HIV
    0.49
    egas
    0.49
     programs
    0.48
    POSITIVE LOGITS
    逶
    0.49
     बचा
    0.49
     தெரிவி
    0.48
     sobretudo
    0.48
    yı
    0.48
    Przeczytaj
    0.48
     बनाई
    0.48
    yoruz
    0.48
    currentIndex
    0.48
     அமைந்துள்ளது
    0.47
    Activations Density 0.000%

    No Known Activations