© 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. 43935
    Prev
    Next
    INDEX
    Explanations

    salvation by faith

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

    often focuses on

    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
     ૩
    0.44
     پوچھ
    0.42
    ৩৫
    0.42
    しかも
    0.41
    avras
    0.41
    ాత్ర
    0.41
     thirty
    0.41
     ціка
    0.41
    ༣
    0.41
     وذلك
    0.40
    POSITIVE LOGITS
     ensamb
    0.45
    桀
    0.43
     jean
    0.42
     nered
    0.42
     tvr
    0.41
     poprzed
    0.41
     jasa
    0.40
    塞
    0.40
     Vertrieb
    0.40
     restaurantes
    0.39
    Activations Density 0.000%

    No Known Activations