© 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. 5667
    Prev
    Next
    INDEX
    Explanations

    or, which, either

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

    alternatives or conditions

    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
     ہے۔
    0.42
    جميع
    0.40
    。
    0.39
     mesmos
    0.38
    بعض
    0.37
     değildir
    0.36
     està
    0.36
     ہیں۔
    0.35
     sådan
    0.35
     achats
    0.35
    POSITIVE LOGITS
     we
    0.55
     which
    0.47
    which
    0.45
    あるいは
    0.44
    we
    0.43
    n
    0.41
     however
    0.40
    もしくは
    0.39
    and
    0.39
    または
    0.38
    Activations Density 0.361%

    No Known Activations