© 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. 74394
    Prev
    Next
    INDEX
    Explanations

    specific services and products

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

    wholesale safety, CL office, data-driven, fundoshi’s, after COVID

    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
     mesela
    0.47
     онлайн
    0.44
     букмекер
    0.43
     FAQs
    0.43
    гӀ
    0.42
     seznam
    0.42
    ઃ
    0.42
     subito
    0.40
     kēia
    0.40
    ે
    0.40
    POSITIVE LOGITS
     reconstituted
    0.42
     까지
    0.41
    rael
    0.40
     colonies
    0.38
     transfected
    0.37
    acrylate
    0.37
     villagers
    0.35
    swald
    0.35
    uspended
    0.35
    nto
    0.35
    Activations Density 0.151%

    No Known Activations