© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7895
    Prev
    Next
    INDEX
    Explanations

    understanding errors and you

    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
    agai
    0.89
    whom
    0.85
     gladly
    0.85
    ად
    0.85
    ⅴ
    0.84
    рье
    0.80
     autoradi
    0.80
     whom
    0.80
    apal
    0.80
    を通じて
    0.79
    POSITIVE LOGITS
     [
    1.02
     [...
    0.95
     [$
    0.94
     Line
    0.90
     ***
    0.90
     Could
    0.90
     Caught
    0.90
     [...]
    0.90
     Object
    0.89
     Unknown
    0.89
    Activations Density 0.063%

    No Known Activations