© 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. 10-GEMMASCOPE-RES-131K
    7. 59182
    Prev
    Next
    INDEX
    Explanations

    place names, locations

    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
     two
    -1.33
    importance
    -1.29
     artikkeli
    -1.28
    ienie
    -1.24
    PLICATIONS
    -1.23
    AKERS
    -1.22
     ormai
    -1.21
    平等
    -1.21
     signore
    -1.19
    وفق
    -1.18
    POSITIVE LOGITS
     reducido
    1.38
     erste
    1.36
    描いた
    1.34
     razonable
    1.34
     peligroso
    1.34
    齟
    1.33
    ubblica
    1.30
    時々
    1.29
     ligeramente
    1.27
    amanan
    1.25
    Activations Density 0.175%

    No Known Activations