© 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. 58765
    Prev
    Next
    INDEX
    Explanations

    bar soap version

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

    structured lists and explanations

    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
     आयोग
    0.62
     ගැ
    0.51
     ആദ്യ
    0.49
     ते
    0.49
     මෙය
    0.49
     तु
    0.48
    dear
    0.48
     ө
    0.48
     સા
    0.48
     թ
    0.48
    POSITIVE LOGITS
     Crypto
    0.46
     Expires
    0.45
    Ê
    0.42
     expiring
    0.41
     Pharmacol
    0.41
     resumen
    0.41
    프트
    0.41
     Webster
    0.40
    Expire
    0.40
     Marcus
    0.40
    Activations Density 0.000%

    No Known Activations