© 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. 62881
    Prev
    Next
    INDEX
    Explanations

    specific words and following words

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

    cryptography and programming constructs

    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
    p
    0.47
    urp
    0.46
     tendance
    0.46
     зад
    0.46
    あと
    0.46
    傾向
    0.46
     потен
    0.45
     дет
    0.44
    panel
    0.44
    ",[],"
    0.44
    POSITIVE LOGITS
    ย
    0.46
     Oil
    0.46
    জ্জিত
    0.46
    жей
    0.45
    ¯
    0.45
    ㅏ
    0.44
     Visa
    0.43
     Jl
    0.43
     Qui
    0.43
     jellyfish
    0.43
    Activations Density 0.000%

    No Known Activations