© 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. 120473
    Prev
    Next
    INDEX
    Explanations

    without charge or removal

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

    need space, credit, seeds

    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
     واع
    0.49
     sauces
    0.48
    unicorn
    0.48
    于是
    0.47
     نہیں۔
    0.47
    scraper
    0.47
     recob
    0.45
    )[
    0.45
    perf
    0.45
     मोटरसा
    0.45
    POSITIVE LOGITS
    غي
    0.51
    atrième
    0.49
     een
    0.48
     derde
    0.46
    חל
    0.46
     "*
    0.46
    نت
    0.45
    ్రి
    0.44
    ்சி
    0.44
     చెర్రీ
    0.44
    Activations Density 0.000%

    No Known Activations