© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13073
    Prev
    Next
    INDEX
    Explanations

    casts long, knock on

    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
    '
    1.66
     mainland
    1.63
    ’
    1.60
    ified
    1.55
     Island
    1.53
     Towers
    1.52
    west
    1.51
     House
    1.46
     deserts
    1.43
     South
    1.43
    POSITIVE LOGITS
     arxivləşdirilib
    2.11
    Calculate
    2.03
    På
    1.91
    ;}
    1.89
    Insufficient
    1.88
    않
    1.86
    CHREIB
    1.84
    cpu
    1.83
    nicht
    1.82
    క్కువ
    1.81
    Activations Density 0.055%

    No Known Activations