© 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. 9193
    Prev
    Next
    INDEX
    Explanations

    .gov domains

    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
     :
    0.84
    ():
    0.73
    ,
    0.71
    ):
    0.69
    :
    0.69
     ?
    0.69
     toma
    0.68
     :(
    0.68
     Donald
    0.67
     Decision
    0.67
    POSITIVE LOGITS
    assertions
    1.21
    proteins
    1.20
    organisms
    1.18
    BPACK
    1.17
    <unused1834>
    1.16
     ব্যাগ
    1.16
     অয়েল
    1.13
    aphthal
    1.12
    spectra
    1.12
    duplicated
    1.11
    Activations Density 0.000%

    No Known Activations