© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1173
    Prev
    Next
    INDEX
    Explanations

    woodland creatures and fables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     PSD
    0.69
     Soder
    0.67
    PSD
    0.66
    愴
    0.63
     sidang
    0.61
    ويه
    0.61
    咵
    0.61
    绛
    0.60
    醮
    0.58
    法施行
    0.58
    POSITIVE LOGITS
     rabbits
    3.42
     squirrels
    3.22
     frogs
    3.16
     animals
    3.08
     monkeys
    3.08
     birds
    3.07
     reptiles
    3.06
     elephants
    3.03
     lizards
    3.03
     tigers
    3.02
    Activations Density 1.696%

    No Known Activations