© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    multilingual technical terms

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

    found the, way to, will do

    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
    on
    0.51
    i
    0.50
     également
    0.50
    2
    0.49
     and
    0.48
    y
    0.48
    s
    0.48
    /
    0.47
    un
    0.45
    e
    0.44
    POSITIVE LOGITS
     prostitutes
    0.50
     열심히
    0.49
    古い
    0.47
     треба
    0.46
     benutzt
    0.45
     benutzen
    0.45
     tumeurs
    0.45
     longitudine
    0.45
     chromatographed
    0.45
     そんな
    0.45
    Activations Density 0.088%

    No Known Activations