© 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. 45506
    Prev
    Next
    INDEX
    Explanations

    good value or venues

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

    size comparison: large to smaller

    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
    ނީ
    0.46
     وإ
    0.45
     esc
    0.45
    Proyecto
    0.44
    變化
    0.43
    喽
    0.43
    esc
    0.42
     أم
    0.42
    后
    0.40
     ہم
    0.40
    POSITIVE LOGITS
    ব্লিউ
    0.43
    /-/
    0.42
    ▫
    0.42
     SUCCESSFULLY
    0.42
    aku
    0.41
    akot
    0.41
    ojen
    0.40
    ￭
    0.40
     thiểu
    0.40
     Accounting
    0.40
    Activations Density 0.000%

    No Known Activations