© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9355
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    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_22_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
     Ага
    1.07
     ञ
    1.05
     ===========
    1.03
     -------------
    1.02
     |-
    1.01
    DummyView
    0.99
     антен
    0.99
    imantan
    0.98
    dV
    0.98
    anamo
    0.98
    POSITIVE LOGITS
    ******
    1.24
    *********
    1.20
    ********
    1.19
    ****************
    1.17
    **********
    1.11
    **
    1.10
    ************
    1.09
    *********/
    1.07
    ***************
    1.04
    ****
    1.04
    Activations Density 0.004%

    No Known Activations