© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1559
    Prev
    Next
    INDEX
    Explanations

    creative output pieces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     a
    0.69
     and
    0.68
     the
    0.67
    k
    0.67
      
    0.67
    0.64
     k
    0.63
    o
    0.63
     people
    0.62
    <start_of_image>
    0.62
    POSITIVE LOGITS
    TGFuZ
    1.55
    𒋀
    1.52
     ہُما
    1.51
    𒄖
    1.51
    fnamefont
    1.50
    Therates
    1.49
    Consentiti
    1.49
     kttt
    1.49
    𒁾
    1.49
    padă
    1.49
    Activations Density 0.317%

    No Known Activations