© 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. 72395
    Prev
    Next
    INDEX
    Explanations

    vacuum tube

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

    concepts and relations

    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
    yn
    0.53
     $)$
    0.51
    >&
    0.49
    ytra
    0.45
     $($
    0.44
    )&
    0.44
    ্ত্র
    0.44
     enzymes
    0.43
     जातो
    0.43
     an
    0.42
    POSITIVE LOGITS
    Performance
    0.50
    ガ
    0.46
    Architecture
    0.45
     Reproduction
    0.45
    体の
    0.44
    性能
    0.43
     Lokal
    0.43
    றுத்த
    0.43
     Performance
    0.43
    іль
    0.42
    Activations Density 0.000%

    No Known Activations