© 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. 8857
    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
     ప్రారం
    0.76
     ...
    0.73
    ...
    0.72
     …
    0.71
     ..
    0.70
    രോധ
    0.68
    [...]
    0.65
    時刻
    0.65
    なり
    0.64
    ...,
    0.63
    POSITIVE LOGITS
    Angular
    1.23
     jQuery
    1.22
    OpenJDK
    1.22
     nucleons
    1.21
     jdk
    1.21
    #![
    1.21
     Stones
    1.20
     JDK
    1.20
    package
    1.17
    jQuery
    1.17
    Activations Density 0.026%

    No Known Activations