© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12347
    Prev
    Next
    INDEX
    Explanations

    repeating sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    ي
    2.08
    y
    2.00
    يًا
    1.97
    i
    1.85
    ات
    1.78
    قدم
    1.76
    り
    1.68
    <em>
    1.68
    ర
    1.68
    ه
    1.66
    POSITIVE LOGITS
     lucht
    2.02
     cudd
    1.99
     cuddle
    1.95
     hillside
    1.95
     hearings
    1.93
     boobs
    1.92
     celebs
    1.89
     kleuren
    1.87
     critters
    1.86
     estrellas
    1.85
    Activations Density 0.029%

    No Known Activations