© 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. 158673
    Prev
    Next
    INDEX
    Explanations

    expressly granted

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

    locations, times, or tasks

    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
    রোগ
    0.62
    requested
    0.52
     километров
    0.48
    शिवम
    0.48
    köz
    0.47
     श्रमिक
    0.47
    簀
    0.46
    渤
    0.46
    eas
    0.46
    塁
    0.45
    POSITIVE LOGITS
    0.64
     publiés
    0.51
     mRNA
    0.48
     emblematic
    0.47
     Handbook
    0.46
    ://
    0.46
     It
    0.44
     morale
    0.44
     unequ
    0.44
     இச
    0.43
    Activations Density 0.000%

    No Known Activations