© 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. 237261
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
     postdoc
    0.49
     lesbian
    0.45
     প্রবেশের
    0.45
    を楽しむ
    0.44
     பணிகள்
    0.42
    /#{
    0.42
    ungkinan
    0.42
     humid
    0.41
     composants
    0.41
     некоторых
    0.40
    POSITIVE LOGITS
     сели
    0.43
    LEA
    0.41
    IGER
    0.40
    公式
    0.40
    霰
    0.40
    mler
    0.39
     ließ
    0.39
     имел
    0.39
     schlecht
    0.39
     lutego
    0.39
    Activations Density 0.000%

    No Known Activations