© 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. 189277
    Prev
    Next
    INDEX
    Explanations

    electronics coupon

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

    concepts and variables

    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
    iy
    0.47
     সেক্ট
    0.47
     پیدا
    0.47
    形
    0.46
     یا
    0.46
     Diwali
    0.45
    دار
    0.45
    ania
    0.44
    έχ
    0.44
    tal
    0.44
    POSITIVE LOGITS
     acknowledge
    0.49
     الليل
    0.48
     necessitate
    0.47
     цар
    0.46
     singleRun
    0.45
     acres
    0.44
     tessel
    0.43
     randomize
    0.43
    ɕ
    0.43
    CSharp
    0.43
    Activations Density 0.000%

    No Known Activations