© 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. 124559
    Prev
    Next
    INDEX
    Explanations

    handles any; Islands.; way the

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

    corporate entity specifics

    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
     المج
    0.51
     اقت
    0.46
     于
    0.46
    อัล
    0.46
     المجال
    0.45
    $-[
    0.45
     โปร
    0.44
     كانت
    0.42
     تنا
    0.42
     غير
    0.42
    POSITIVE LOGITS
     inverter
    0.53
     presentes
    0.50
    इसमें
    0.50
     stk
    0.50
     registr
    0.49
     registra
    0.48
     incidents
    0.48
     stung
    0.48
    ᱓
    0.47
    भार
    0.47
    Activations Density 0.000%

    No Known Activations