© 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. 165279
    Prev
    Next
    INDEX
    Explanations

    tasked with, circuit works, evil eye

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

    Water Effects

    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
    （
    0.47
    ;\
    0.46
     Montréal
    0.45
    އ
    0.44
    အောင်
    0.44
    不必
    0.43
     GERM
    0.43
    ফেট
    0.43
    是一
    0.42
     organisiert
    0.42
    POSITIVE LOGITS
    மாகவும்
    0.54
    ్యా
    0.46
    וט
    0.43
    覂
    0.42
    ונ
    0.41
    溏
    0.41
     Sald
    0.41
     ይሰ
    0.41
    لام
    0.40
     संस्कृति
    0.40
    Activations Density 0.000%

    No Known Activations