© 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. 73511
    Prev
    Next
    INDEX
    Explanations

    projects and outcomes

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

    defines semantic roles

    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
    订
    0.48
    డింది
    0.46
     गुणनखंड
    0.46
     figuring
    0.45
    ibri
    0.45
    .°
    0.45
    ద్ది
    0.44
    ाइब
    0.44
     youre
    0.44
    ም።
    0.44
    POSITIVE LOGITS
     promov
    0.44
    槅
    0.44
    ו
    0.43
     $[
    0.43
    TargetFramework
    0.43
    ոչ
    0.42
    on
    0.41
    메라
    0.40
    ტერ
    0.39
     unint
    0.38
    Activations Density 0.000%

    No Known Activations