© 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. 22-GEMMASCOPE-RES-131K
    7. 26098
    Prev
    Next
    INDEX
    Explanations

    looping and continuing

    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_22/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
     enggak
    -0.88
    famille
    -0.84
    boucles
    -0.83
    Masukkan
    -0.82
     navideña
    -0.79
    футбо
    -0.79
     menyebutkan
    -0.78
    buen
    -0.77
    Berat
    -0.76
     綺麗
    -0.76
    POSITIVE LOGITS
     still
    1.08
     continuing
    1.03
     ещё
    1.02
     еще
    0.98
     ancora
    0.95
    ++;
    0.93
     continue
    0.92
    tuce
    0.88
     anymore
    0.88
     remaining
    0.88
    Activations Density 0.013%

    No Known Activations