© 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. 10156
    Prev
    Next
    INDEX
    Explanations

    chosen! Month for size of

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

    around the

    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
     často
    0.38
     warto
    0.37
    ++++
    0.35
    امت
    0.35
     unsightly
    0.35
    Bras
    0.34
     brav
    0.34
    prz
    0.34
    Bran
    0.34
    чатку
    0.34
    POSITIVE LOGITS
    ंपूर्वी
    0.47
    ট্ট
    0.44
     Möglich
    0.44
     Petition
    0.43
    ydı
    0.43
    ͗
    0.42
    ANO
    0.41
     মোহন
    0.41
     Phòng
    0.41
    avacanam
    0.41
    Activations Density 0.000%

    No Known Activations