© 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. 1179
    Prev
    Next
    INDEX
    Explanations

    goals scored

    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
     timescales
    0.77
     timescale
    0.75
     manoe
    0.74
     competir
    0.74
     supervivencia
    0.74
     juara
    0.73
     renom
    0.71
    侔
    0.70
     railways
    0.70
     утвер
    0.69
    POSITIVE LOGITS
     assists
    1.22
     tallied
    1.18
     Assists
    1.11
     scored
    1.09
     assist
    1.06
     scoreless
    1.05
     scoring
    1.02
     career
    1.00
     strikeouts
    0.99
     totaled
    0.97
    Activations Density 0.515%

    No Known Activations