© 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. 69808
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific words

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

    principles and concepts

    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
    erman
    0.48
    g
    0.47
    si
    0.47
    ge
    0.46
    s
    0.46
    la
    0.45
    ει
    0.45
    le
    0.44
    ier
    0.44
    re
    0.44
    POSITIVE LOGITS
     Акы
    0.58
    入れ
    0.56
     そこ
    0.54
     ስርዓ
    0.52
     لوی
    0.52
     रखती
    0.52
     ஆர்வ
    0.52
     Uniwers
    0.52
     त्यात
    0.51
     رکھنے
    0.51
    Activations Density 0.000%

    No Known Activations