© 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. 13-GEMMASCOPE-2-RES-16K
    7. 9524
    Prev
    Next
    INDEX
    Explanations

    highest continuous

    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_13_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
     voglia
    1.48
    炵
    1.42
    aaaaaaaa
    1.41
     dieci
    1.40
    Ꮼ
    1.37
    Traffic
    1.36
     měla
    1.35
     pueda
    1.35
    aaaa
    1.35
     vouloir
    1.34
    POSITIVE LOGITS
     ins
    0.91
    sohn
    0.88
    scn
    0.84
     ब्राउन
    0.82
    ydd
    0.82
     (@
    0.80
     (
    0.79
     규
    0.78
     RBC
    0.77
     TCM
    0.77
    Activations Density 0.000%

    No Known Activations