© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 580
    Prev
    Next
    INDEX
    Explanations

    sports competition outcomes

    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
     அரசின்
    0.84
     juris
    0.81
     DOE
    0.80
     FHWA
    0.79
     Radiat
    0.78
     세포
    0.76
     tritium
    0.76
    뽁
    0.74
    Arduino
    0.73
     disulfide
    0.72
    POSITIVE LOGITS
     midfielder
    2.22
     midfielders
    2.16
     Tottenham
    2.10
     UEFA
    2.08
     midfield
    2.06
     footballers
    2.06
     Atletico
    2.05
     Arsenal
    2.04
     Mourinho
    2.03
     Football
    2.01
    Activations Density 0.966%

    No Known Activations