© 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. 1994
    Prev
    Next
    INDEX
    Explanations

    excessive degree

    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
     comerciantes
    1.79
    TextureAsset
    1.69
    opharmaceuticals
    1.67
    offsetof
    1.67
    ","/
    1.65
    ibrary
    1.63
    copyOf
    1.62
    িস্থ
    1.59
     convenience
    1.59
    OURCES
    1.59
    POSITIVE LOGITS
    চরণ
    1.89
    なんか
    1.87
     Regist
    1.85
    Па
    1.84
     па
    1.83
     کو
    1.81
    It
    1.81
     usp
    1.77
    ﮢ
    1.76
    شاف
    1.76
    Activations Density 0.336%

    No Known Activations