© 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. 31521
    Prev
    Next
    INDEX
    Explanations

    foreign language and legal terms

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

    skills for environments

    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
     but
    0.51
    Ф
    0.50
    Ư
    0.49
     மிகப்பெரிய
    0.48
    天的
    0.46
    朝着
    0.46
    洛
    0.46
    
    0.45
     ions
    0.44
     sted
    0.44
    POSITIVE LOGITS
    anque
    0.49
     chiffre
    0.48
     فیصلے
    0.48
     laiss
    0.47
     échelle
    0.46
     اعلی
    0.46
     petitioner
    0.45
    вое
    0.43
    z
    0.43
     फैसले
    0.43
    Activations Density 0.000%

    No Known Activations