© 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. 71687
    Prev
    Next
    INDEX
    Explanations

    website content and links

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

    arguments, analysis, discussion

    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
    उन्होंने
    0.47
     Moderate
    0.45
     Rear
    0.42
     scan
    0.41
     와
    0.41
     هنگ
    0.41
    SHOP
    0.41
    hrm
    0.40
     انہوں
    0.40
     krishna
    0.40
    POSITIVE LOGITS
    恴
    0.54
     eventuali
    0.53
     dotycz
    0.53
     emozioni
    0.52
     irgende
    0.52
    經驗
    0.51
     débil
    0.51
    迳
    0.51
     condições
    0.50
     rifless
    0.50
    Activations Density 0.001%

    No Known Activations