© 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. 9248
    Prev
    Next
    INDEX
    Explanations

    Psychology Today

    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
    Soft
    1.32
    Flex
    1.30
    .;
    1.29
    _
    1.27
    .+
    1.23
    _*
    1.23
    Weight
    1.22
     Flex
    1.20
    ._
    1.19
     Soft
    1.18
    POSITIVE LOGITS
     spoiling
    1.03
     either
    0.91
    jsonplaceholder
    0.87
    either
    0.81
     overwhelmingly
    0.75
    cloudflare
    0.75
    accumulator
    0.74
    submitted
    0.74
     whichever
    0.74
     plung
    0.74
    Activations Density 0.018%

    No Known Activations