© 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. 5535
    Prev
    Next
    INDEX
    Explanations

    phrases following commas

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

    was, is now

    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
     the
    0.38
     those
    0.35
    ，
    0.34
    The
    0.31
    िया
    0.31
    那些
    0.31
    ان
    0.30
    所有的
    0.30
    爾
    0.30
    我们会
    0.30
    POSITIVE LOGITS
     mutta
    0.40
     ngunit
    0.38
     doesn
    0.38
     incluye
    0.37
     включает
    0.35
     പക്ഷേ
    0.35
     creates
    0.35
     includes
    0.34
     tiene
    0.34
    bao
    0.34
    Activations Density 0.047%

    No Known Activations