© 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. 55912
    Prev
    Next
    INDEX
    Explanations

    ensuring quality and care

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

    emerging, patients, failing, lives

    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
    вард
    0.47
    ές
    0.46
     जाएँ
    0.45
     функції
    0.45
    μέ
    0.44
    רון
    0.44
    MaxPool
    0.44
    겐
    0.43
    髡
    0.43
    리
    0.43
    POSITIVE LOGITS
    ingt
    0.50
     That
    0.49
     Sometimes
    0.47
     बंद
    0.47
     ഒറ്റ
    0.45
    sold
    0.44
    ih
    0.43
    fir
    0.42
     hing
    0.42
    इनस
    0.42
    Activations Density 0.000%

    No Known Activations