© 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. 23861
    Prev
    Next
    INDEX
    Explanations

    the quality of my work

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

    equivalent concepts across languages

    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
    .。
    0.50
     매우
    0.49
    ®.
    0.48
    ።
    0.48
    ։
    0.46
    ९
    0.46
    ()}.
    0.44
    *.
    0.44
    ).}
    0.42
    .\
    0.41
    POSITIVE LOGITS
     oneself
    0.51
    而非
    0.46
     is
    0.45
    するのは
    0.45
     versus
    0.44
    るのは
    0.44
    したのは
    0.41
     είναι
    0.41
     esclusivamente
    0.39
     magari
    0.39
    Activations Density 0.177%

    No Known Activations