© 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. 1825
    Prev
    Next
    INDEX
    Explanations

    position ahead, self-control, obligation

    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
    2
    1.21
    6
    1.05
    one
    1.02
    1
    1.01
    3
    0.99
    Explanation
    0.97
    ሁ
    0.97
    4
    0.96
    5
    0.95
    whereas
    0.95
    POSITIVE LOGITS
     bount
    1.30
     protease
    1.28
     最高
    1.27
     hugely
    1.25
    强大
    1.24
     wildly
    1.22
     autoridades
    1.22
     prowess
    1.21
     proteolytic
    1.20
     titan
    1.20
    Activations Density 0.044%

    No Known Activations