© 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. 152298
    Prev
    Next
    INDEX
    Explanations

    foreign language or technical terms

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

    influenced by or dependent 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
    ler
    0.43
     implemented
    0.43
    ([...
    0.42
    =''
    0.42
    =
    0.41
    =[
    0.41
    outes
    0.40
     empowering
    0.40
     Spotify
    0.39
     Ebay
    0.39
    POSITIVE LOGITS
     profe
    0.46
     alumin
    0.44
     सप्ताह
    0.44
     wanneer
    0.44
    焊
    0.44
     metal
    0.43
     lorsqu
    0.43
     zarówno
    0.43
     molyb
    0.42
     humide
    0.42
    Activations Density 0.000%

    No Known Activations