© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 2239
    Prev
    Next
    INDEX
    Explanations

    program setup examples

    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_17_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
    ਣੀ
    1.16
     Marker
    1.12
    нией
    1.11
    ஞர்
    1.09
    ⁡
    1.09
     道
    1.06
    ющими
    1.03
     UIStoryboard
    1.02
     작성
    1.02
     بنائے
    1.02
    POSITIVE LOGITS
     else
    1.04
    else
    0.91
    ]);
    0.82
    elit
    0.80
    .[
    0.79
     '.';
    0.76
    ellen
    0.73
    ELSE
    0.73
    ']);
    0.73
     assimilate
    0.73
    Activations Density 0.001%

    No Known Activations