© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 2285
    Prev
    Next
    INDEX
    Explanations

    programming function calls

    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
    (
    1.38
    (){
    1.31
    ():
    1.30
    (),
    1.25
    ()
    1.21
    ().
    1.19
    (@
    1.17
    (_
    1.16
    ()[
    1.15
    ()+
    1.14
    POSITIVE LOGITS
     Kamp
    0.65
     angeboten
    0.64
    ereza
    0.64
    haan
    0.63
    emies
    0.63
     Meer
    0.63
     mogu
    0.62
    ksam
    0.62
     Wirkung
    0.60
     Rejo
    0.59
    Activations Density 0.000%

    No Known Activations