© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11540
    Prev
    Next
    INDEX
    Explanations

    prematurity, today, Qatar, win, player, morning, gross

    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
    e
    1.82
    ي
    1.77
     The
    1.73
    h
    1.60
    The
    1.56
    يّ
    1.52
    ب
    1.49
    och
    1.49
    ت
    1.45
    eh
    1.44
    POSITIVE LOGITS
    
    2.18
    궪
    2.18
     স্বীকৃতির
    2.18
    _{+}+
    2.14
    꼫
    2.12
     अफेयर्स
    2.10
     batter
    2.05
    DAYS
    2.02
    
    2.02
    
    2.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.