© 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. 157077
    Prev
    Next
    INDEX
    Explanations

    accommodation with services

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

    before epidemic, settings, hardware

    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
    шу
    0.46
     fevere
    0.46
    ри
    0.45
    f
    0.43
    他說
    0.43
    는데
    0.42
    他在
    0.42
     purview
    0.42
    fier
    0.41
    eness
    0.41
    POSITIVE LOGITS
     Vieni
    0.49
     Nürnberg
    0.48
     propietarios
    0.47
     Comune
    0.46
     Banca
    0.46
     Geschäfts
    0.46
    𝓬
    0.46
     Fácil
    0.45
     Oğ
    0.45
    各有
    0.45
    Activations Density 0.000%

    No Known Activations