© 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. 193629
    Prev
    Next
    INDEX
    Explanations

    email address

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

    tune for

    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
     sleeve
    0.53
     Server
    0.50
     Amer
    0.49
     Above
    0.49
     屋
    0.49
     フォト
    0.47
     電
    0.47
     Huss
    0.47
     Америка
    0.47
     С
    0.46
    POSITIVE LOGITS
    नहीं
    0.50
    也是
    0.45
    INFE
    0.45
    LVANIA
    0.45
    神奇
    0.43
    मिस्ट्री
    0.42
    넝
    0.42
     tắt
    0.42
     també
    0.41
     infección
    0.41
    Activations Density 0.002%

    No Known Activations