© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10192
    Prev
    Next
    INDEX
    Explanations

    author followed by a descriptor

    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
    Ꮆ
    2.16
    髅
    2.09
    œil
    2.07
     “‘
    2.01
    сім
    1.97
    мены
    1.95
    з
    1.94
    應用
    1.93
    वानिव
    1.93
     đá
    1.92
    POSITIVE LOGITS
    ing
    2.34
    .".,
    2.08
    .'"
    2.05
    ."-
    2.05
    ."
    1.97
    '."
    1.95
    یه
    1.90
    .")
    1.90
    werten
    1.87
    ."'
    1.87
    Activations Density 0.026%

    No Known Activations