© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8896
    Prev
    Next
    INDEX
    Explanations

    places and political entities

    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_10/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
     such
    -1.56
    と同じ
    -1.07
     près
    -1.05
    开车
    -1.05
     Besten
    -1.02
    шения
    -1.02
     pourraient
    -1.02
    𓆏
    -1.01
     таких
    -1.00
     VARIOUS
    -1.00
    POSITIVE LOGITS
     now
    1.27
     as
    1.27
     additional
    1.21
     with
    1.12
     within
    1.09
     will
    1.05
    月末
    1.04
     संस्
    1.03
     to
    1.02
    gapa
    1.01
    Activations Density 0.173%

    No Known Activations