© 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. 11874
    Prev
    Next
    INDEX
    Explanations

    describing the use of functions

    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
     ausp
    1.05
     rel
    1.03
    gleich
    0.97
    ise
    0.96
    ī
    0.95
     to
    0.94
    iri
    0.92
    popular
    0.92
     inspect
    0.92
    adir
    0.92
    POSITIVE LOGITS
    <unused1352>
    1.43
    <unused1562>
    1.43
    <unused1497>
    1.42
    Ꮬ
    1.41
     spasms
    1.40
    㩴
    1.40
    <unused1699>
    1.38
    Ꮰ
    1.37
    <unused1500>
    1.37
    <unused1343>
    1.37
    Activations Density 0.079%

    No Known Activations