© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98910
    Prev
    Next
    INDEX
    Explanations

    links, TP Link, Despite progress, Click, Price

    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
    motherapy
    -0.85
    หลัง
    -0.83
    Badge
    -0.82
    匐
    -0.82
    lexic
    -0.82
    铢
    -0.82
     Univer
    -0.79
    @[+][
    -0.79
    ROID
    -0.77
     uLocal
    -0.77
    POSITIVE LOGITS
    Transkript
    0.75
    наче
    0.73
     ediyor
    0.71
     basa
    0.70
    Witam
    0.70
     asig
    0.70
    Bonsoir
    0.69
     sigu
    0.69
    Доброго
    0.69
     lavori
    0.69
    Activations Density 0.000%

    No Known Activations