© 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. 51579
    Prev
    Next
    INDEX
    Explanations

    describing actions, qualities, or things

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

    Manual, Lithium, ability

    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
     checkBox
    0.52
     გვ
    0.50
     went
    0.49
     言っ
    0.48
     this
    0.48
     ሌ
    0.48
     schermo
    0.48
     forbade
    0.47
     leaving
    0.46
     HERE
    0.46
    POSITIVE LOGITS
    өл
    0.52
    نت
    0.51
    تد
    0.50
    د
    0.48
    Upgradeable
    0.47
    FEC
    0.47
    دن
    0.46
    ذ
    0.46
    <0xE4>
    0.45
    دی
    0.45
    Activations Density 0.000%

    No Known Activations