© 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. 126565
    Prev
    Next
    INDEX
    Explanations

    following or preceding certain words

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

    influenced by

    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
    اط
    0.43
     Jeffery
    0.43
     UserController
    0.43
    ；
    0.43
    ｆ
    0.42
    ళ
    0.42
    必須
    0.41
    Simplify
    0.41
     Perpetual
    0.41
    翮
    0.41
    POSITIVE LOGITS
     страны
    0.54
     काग
    0.52
     hänen
    0.48
     چون
    0.48
     그냥
    0.48
     ওর
    0.47
    ្សា
    0.47
    smiley
    0.47
     hauteur
    0.47
     gesch
    0.46
    Activations Density 0.000%

    No Known Activations