© 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. 217034
    Prev
    Next
    INDEX
    Explanations

    URLs and references

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

    Dialog, humiliation, mesas, tube

    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
     <!--<
    0.52
     azo
    0.50
     Cobra
    0.49
     Nid
    0.49
     mum
    0.47
     Unable
    0.47
     subcontractor
    0.47
     geek
    0.46
     cyclohex
    0.45
     ejac
    0.45
    POSITIVE LOGITS
    옮
    0.47
    ي
    0.47
    負担
    0.46
    мыми
    0.45
    št
    0.45
    АТ
    0.44
    ឡើង
    0.44
    ಷ್ಣ
    0.44
    ܗ
    0.44
    のですが
    0.43
    Activations Density 0.001%

    No Known Activations