© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30862
    Prev
    Next
    INDEX
    Explanations

    copious, profuse, abundant flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    謐
    -0.80
    pagesize
    -0.70
    liśmy
    -0.69
    ँच
    -0.68
    سة
    -0.67
    fficiencies
    -0.66
    LastError
    -0.66
    letek
    -0.64
    Updater
    -0.64
     直接
    -0.64
    POSITIVE LOGITS
     copious
    2.89
     profuse
    2.80
     abundant
    2.75
     prolific
    2.75
    abund
    2.58
     Abund
    2.48
     abundante
    2.33
    Abund
    2.33
     heavy
    2.30
     оби
    2.25
    Activations Density 0.063%

    No Known Activations