© 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. 1574
    Prev
    Next
    INDEX
    Explanations

    sounds and volume

    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
     covalent
    0.68
    渶
    0.67
    拈
    0.67
     váy
    0.64
     altın
    0.63
    क्रमण
    0.62
    зяржа
    0.62
     capill
    0.62
    蓿
    0.61
     skincare
    0.61
    POSITIVE LOGITS
     loud
    2.83
     louder
    2.81
     noises
    2.80
     noise
    2.67
     loudest
    2.59
    声音
    2.57
     loudly
    2.50
    的声音
    2.49
    聲音
    2.46
     sounds
    2.45
    Activations Density 0.933%

    No Known Activations