© 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. 231865
    Prev
    Next
    INDEX
    Explanations

    designs and products

    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
    äten
    0.46
    ില്ല
    0.45
    dct
    0.44
    m
    0.44
    it
    0.44
    ਿਲ
    0.44
    डल
    0.44
     doigt
    0.43
    вають
    0.43
    τσ
    0.43
    POSITIVE LOGITS
     apocalypse
    0.54
     ve
    0.52
     system
    0.50
     وده
    0.46
    集團
    0.45
    0.44
    arden
    0.44
     UDP
    0.44
    在
    0.44
     uygulama
    0.43
    Activations Density 0.000%

    No Known Activations