© 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. 183902
    Prev
    Next
    INDEX
    Explanations

    names and specific international words

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

    potential threats

    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
    utilisation
    0.53
     അല്ലെങ്കിൽ
    0.52
     utilização
    0.51
    ols
    0.50
     используется
    0.49
    repe
    0.48
     复
    0.48
    challenged
    0.48
    sru
    0.47
    šću
    0.47
    POSITIVE LOGITS
    なの
    0.50
     wand
    0.46
    District
    0.42
    Daisy
    0.41
     belle
    0.41
    平
    0.41
     daisy
    0.40
    ฉ
    0.40
    捧
    0.39
     Hamlin
    0.39
    Activations Density 0.000%

    No Known Activations