© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217848
    Prev
    Next
    INDEX
    Explanations

    freshness and active engagement

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

    beyond the typical

    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
     unbek
    0.52
    ke
    0.51
    kai
    0.49
    ë
    0.48
    פ
    0.46
    bem
    0.46
    ē
    0.46
    itação
    0.45
    ეთ
    0.45
    kaart
    0.45
    POSITIVE LOGITS
     consultations
    0.55
     rustic
    0.52
     proprietors
    0.52
    詢
    0.52
     freshness
    0.52
     representantes
    0.51
     inqu
    0.51
     flavonoids
    0.49
    UAGES
    0.49
     macarons
    0.49
    Activations Density 0.000%

    No Known Activations