© 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. 77105
    Prev
    Next
    INDEX
    Explanations

    security is not guaranteed

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

    names and titles

    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
     हल्की
    0.48
    spielen
    0.47
    𝗧
    0.46
    लंघन
    0.46
     récentes
    0.46
    n
    0.44
    प्रश्न
    0.44
    끅
    0.44
    💸
    0.43
    अय
    0.43
    POSITIVE LOGITS
    为一个
    0.51
     fir
    0.45
     teg
    0.44
     fung
    0.44
    anska
    0.44
     large
    0.44
    有一个
    0.44
     Marine
    0.43
    到底
    0.43
     McCann
    0.43
    Activations Density 0.002%

    No Known Activations