© 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. 177351
    Prev
    Next
    INDEX
    Explanations

    academic conference proceedings

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

    artificial, fake, sham

    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
     სწ
    0.47
    🌌
    0.47
    ラン
    0.47
    பட
    0.46
    🛰
    0.46
    スン
    0.45
     የመ
    0.45
     ಗಮನ
    0.45
    🏎
    0.44
     உத
    0.43
    POSITIVE LOGITS
    lega
    0.44
     Ply
    0.44
    icago
    0.42
     Balls
    0.42
     Casting
    0.41
     Cubs
    0.40
    alá
    0.40
     Root
    0.40
     Rhino
    0.40
     Ere
    0.40
    Activations Density 0.001%

    No Known Activations