© 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. 2586
    Prev
    Next
    INDEX
    Explanations

    historian names and contexts

    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
     potty
    -0.79
    zyła
    -0.78
    RefreshToken
    -0.75
     Poet
    -0.75
     düğ
    -0.71
    zija
    -0.70
     gezondheid
    -0.70
    acias
    -0.70
    aquin
    -0.70
     Ethernet
    -0.69
    POSITIVE LOGITS
     historians
    2.73
     historian
    2.58
    Hist
    2.33
    hist
    2.20
     Hist
    2.13
     historiador
    2.09
     histor
    2.06
     HIST
    2.05
     Historian
    2.02
     истори
    1.98
    Activations Density 0.048%

    No Known Activations