© 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. 42654
    Prev
    Next
    INDEX
    Explanations

    foreign languages or non-English words

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

    critical unblocking tasks

    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
    ت
    0.60
    i
    0.56
    ere
    0.52
    eb
    0.49
    an
    0.49
    ig
    0.48
    ite
    0.48
    ्ट
    0.48
    cht
    0.48
    l
    0.47
    POSITIVE LOGITS
     Ninth
    0.47
    多个
    0.47
     रोमा
    0.46
    Ending
    0.46
    绔
    0.46
     Según
    0.45
    罗马
    0.45
     Ending
    0.45
     troviamo
    0.45
    态度
    0.44
    Activations Density 0.000%

    No Known Activations