© 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. 59206
    Prev
    Next
    INDEX
    Explanations

    fishermen

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

    can understand

    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
    竺
    0.44
    등
    0.42
    。
    0.42
    ۔
    0.42
    ATIC
    0.42
    ERIC
    0.41
    新兴
    0.40
    ։
    0.40
    Wildlife
    0.40
     ஆகியவற்ற
    0.39
    POSITIVE LOGITS
     voglia
    0.49
    (",");
    0.45
    yar
    0.43
     baisse
    0.43
    pand
    0.43
     প্ল
    0.43
    ority
    0.42
     gaat
    0.41
     রীতি
    0.41
    yukur
    0.41
    Activations Density 0.000%

    No Known Activations