© 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. 93525
    Prev
    Next
    INDEX
    Explanations

    locations and numbers

    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
    Australia
    -1.20
     NYS
    -1.17
    Michigan
    -1.16
    Canada
    -1.09
     NZ
    -1.08
    Florida
    -1.06
    Australian
    -1.05
     Австра
    -1.04
    Queensland
    -1.04
    Colorado
    -1.02
    POSITIVE LOGITS
    並沒有
    0.88
    qtd
    0.82
     north
    0.82
    laund
    0.82
     North
    0.81
    的问
    0.81
     Städten
    0.80
    龐
    0.79
     muk
    0.79
     parro
    0.78
    Activations Density 0.212%

    No Known Activations