© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84237
    Prev
    Next
    INDEX
    Explanations

    losing streak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -2.27
    ropractic
    -2.09
    男性
    -2.08
     неболь
    -2.08
     {
    -2.03
     This
    -2.02
     '';
    -2.02
    商人
    -2.00
     aspire
    -2.00
    。“
    -1.98
    POSITIVE LOGITS
    ーーー
    2.52
    〜〜
    2.50
    ing
    2.25
     losing
    2.22
    with
    2.20
    誒
    2.13
    ro
    2.08
    ating
    2.03
    蠃
    2.02
    を変える
    1.99
    Activations Density 0.002%

    No Known Activations