© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8786
    Prev
    Next
    INDEX
    Explanations

    too much or too many

    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_22_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
     '');
    0.99
    けば
    0.98
    ellen
    0.92
     hả
    0.89
    Indigo
    0.89
    elsen
    0.88
     ',');
    0.87
    $.;
    0.87
    ഫ്
    0.86
    ellent
    0.86
    POSITIVE LOGITS
     many
    2.57
    many
    2.41
     MANY
    2.23
     nhiều
    1.99
     viele
    1.97
     muitos
    1.96
     Many
    1.90
     многих
    1.90
     muchos
    1.85
     banyak
    1.82
    Activations Density 0.111%

    No Known Activations