© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14607
    Prev
    Next
    INDEX
    Explanations

    document section titles

    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
    own
    0.95
    （
    0.90
    alling
    0.90
    oning
    0.88
     honours
    0.88
    ane
    0.88
    use
    0.87
    omy
    0.87
    this
    0.86
     utmost
    0.86
    POSITIVE LOGITS
     ними
    1.39
    Jogador
    1.33
     kişiler
    1.31
    ⿹
    1.31
     individuo
    1.30
    URNIZOR
    1.29
     ObjData
    1.27
    䔋
    1.26
     口
    1.26
    ILayout
    1.26
    Activations Density 0.111%

    No Known Activations