© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    affirmation or thinking sounds

    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
    笉
    0.69
     আখ্যা
    0.67
    
    0.66
    ϩ
    0.65
    விர
    0.65
    任何人
    0.64
    ⁧
    0.63
    下列
    0.63
     ব্যতীত
    0.62
    સ્થા
    0.62
    POSITIVE LOGITS
     oh
    3.16
     Oh
    3.00
     Hmm
    2.81
    Oh
    2.76
     ah
    2.75
     hmm
    2.73
     uh
    2.73
     Uh
    2.71
     Ah
    2.66
    Hmm
    2.52
    Activations Density 1.035%

    No Known Activations