© 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. 2405
    Prev
    Next
    INDEX
    Explanations

    math or currency symbols

    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
    ―
    0.82
     ´
    0.77
     ―
    0.76
    auso
    0.75
    ﾊ
    0.75
    koľ
    0.71
    ɔ
    0.71
    ΄
    0.68
    ங்களைக்
    0.67
    ʌ
    0.67
    POSITIVE LOGITS
     $
    5.38
    $
    4.20
    ，$
    3.60
    -$
    3.59
    、$
    3.55
    ,$
    3.53
     ($
    3.53
    ($
    3.48
    :$
    3.41
     ~$
    3.36
    Activations Density 0.662%

    No Known Activations