© 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. 5000
    Prev
    Next
    INDEX
    Explanations

    numbered and lettered references

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

    legal or section references in parentheses

    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
     Liberties
    0.42
    鍘
    0.42
    Wak
    0.41
     habitudes
    0.41
     gått
    0.40
    क्रो
    0.38
     nuo
    0.38
    มาจาก
    0.38
    渐
    0.38
    Laurie
    0.38
    POSITIVE LOGITS
    iii
    0.57
     clause
    0.48
    items
    0.46
     subparagraph
    0.46
    box
    0.44
    item
    0.44
     clauses
    0.44
    sentence
    0.43
     sentence
    0.42
     mandatory
    0.42
    Activations Density 0.021%

    No Known Activations