© 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. 109132
    Prev
    Next
    INDEX
    Explanations

    practical locations

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

    specific words or phrases

    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
     Bezirk
    0.50
     Filing
    0.46
     getToken
    0.45
     binary
    0.44
     definitively
    0.44
     bic
    0.44
     filed
    0.43
    斌
    0.42
     Bryant
    0.42
    晫
    0.42
    POSITIVE LOGITS
    perception
    0.51
    rafos
    0.50
    ıları
    0.50
    érence
    0.49
    tuvo
    0.49
    hype
    0.49
     पेर
    0.49
    balo
    0.48
     Eindruck
    0.48
    coast
    0.46
    Activations Density 0.002%

    No Known Activations