© 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. 57713
    Prev
    Next
    INDEX
    Explanations

    connecting conferences and relationships

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

    HTML links and attributes

    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
     пола
    0.45
    䣬
    0.42
    묽
    0.42
     Idani
    0.41
    ayakan
    0.40
    Gibson
    0.40
    AppendLine
    0.40
     откло
    0.39
     biopsies
    0.39
    ErrMsg
    0.39
    POSITIVE LOGITS
    是
    0.50
    伙伴
    0.48
     forbind
    0.47
     соеди
    0.45
     connections
    0.43
     conect
    0.43
    preconnect
    0.43
     connecting
    0.43
    는
    0.42
    は
    0.41
    Activations Density 0.003%

    No Known Activations