© 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
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2600
    Prev
    Next
    INDEX
    Explanations

    me following verbs/nouns

    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
    良かった
    0.69
     derivation
    0.68
    よかった
    0.65
     अवलोकन
    0.65
     aria
    0.65
     Coppola
    0.63
    压
    0.62
     Homeless
    0.62
    移
    0.62
     Magna
    0.61
    POSITIVE LOGITS
    unier
    1.10
    isterschaft
    1.07
    ander
    1.04
    andered
    1.02
    andering
    1.01
     encanta
    0.98
    anders
    0.95
     gusta
    0.94
    chandise
    0.92
    ђу
    0.91
    Activations Density 0.088%

    No Known Activations