© 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. 163434
    Prev
    Next
    INDEX
    Explanations

    publishing, brand, invite, rates

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

    opens diagonals or lines

    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
    н
    0.49
    фе
    0.47
    ಕ್ರಮ
    0.47
    톄
    0.46
    спекти
    0.45
    袱
    0.44
    фа
    0.43
    जारी
    0.43
    сць
    0.42
    ㄴ
    0.42
    POSITIVE LOGITS
     enkele
    0.50
     einen
    0.49
    leit
    0.49
     einige
    0.47
     yks
    0.47
     kijk
    0.47
     heran
    0.47
     glee
    0.46
     elekt
    0.46
     कुछ
    0.45
    Activations Density 0.000%

    No Known Activations