© 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
    2. Gemma-3-270M
    3. 12-GEMMASCOPE-2-RES-16K
    4. 5893
    Prev
    Next
    INDEX
    Explanations

    Phase 1 assessment or duration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
    .;
    2.09
    .),
    1.97
     )),
    1.90
    .•
    1.88
    .";
    1.85
     .,
    1.84
    .);
    1.83
    ;.
    1.82
    .).
    1.76
     {,
    1.74
    POSITIVE LOGITS
     Part
    1.94
     thứ
    1.85
     erneut
    1.81
     nochmal
    1.79
     nicht
    1.77
     Thank
    1.76
     Böl
    1.76
     nichts
    1.75
     Forever
    1.75
     allerdings
    1.74
    Activations Density 0.066%

    No Known Activations