© 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. 34279
    Prev
    Next
    INDEX
    Explanations

    listing or connecting items

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

    misspellings and abbreviations

    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
     एखा
    0.53
    Į
    0.52
    ק
    0.52
    י
    0.51
    س
    0.50
    ו
    0.50
    א
    0.49
    ש
    0.48
    </strong>
    0.48
    earn
    0.47
    POSITIVE LOGITS
     alem
    0.45
     generates
    0.43
     hydrology
    0.43
     gathers
    0.43
     humides
    0.42
     alleges
    0.41
     hypoxic
    0.41
     FY
    0.40
     demographic
    0.40
     polyd
    0.40
    Activations Density 0.000%

    No Known Activations