© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102976
    Prev
    Next
    INDEX
    Explanations

    to compare, understand, assessing, evaluating

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

    multilingual text generation

    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
    Negative Logits
     Canadian
    0.54
     CDC
    0.47
     ″
    0.46
     Lessor
    0.45
     and
    0.43
     Granite
    0.43
    itives
    0.42
     Peruvian
    0.42
     Bra
    0.42
     ​​
    0.42
    POSITIVE LOGITS
     आपल्याला
    0.62
     तुम्हाला
    0.51
     музи
    0.49
    自身の
    0.48
    YOU
    0.48
    Deviation
    0.47
     ನೀವು
    0.47
    让你
    0.47
    अपने
    0.47
     음악
    0.47
    Activations Density 0.003%

    No Known Activations