© 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. 243487
    Prev
    Next
    INDEX
    Explanations

    contingency connected lost blog UPS driven

    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
    रोक्त
    0.50
    ICES
    0.46
    ۔
    0.44
    าร
    0.43
    を残
    0.43
    కా
    0.42
    ত্যাশিত
    0.42
    ،
    0.42
    た
    0.41
    Ա
    0.41
    POSITIVE LOGITS
    '
    0.61
    인은
    0.58
    ot
    0.51
     twórc
    0.48
     打
    0.48
    textColour
    0.46
     trabajar
    0.46
     者
    0.46
     INSTR
    0.46
    动手
    0.45
    Activations Density 0.001%

    No Known Activations