© 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. 84260
    Prev
    Next
    INDEX
    Explanations

    geographical and geological features

    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
     they
    -1.43
    噘
    -1.42
     (,
    -1.30
    simply
    -1.28
     inder
    -1.27
     politiche
    -1.26
     importanza
    -1.23
     faptul
    -1.23
    咩
    -1.22
    manın
    -1.21
    POSITIVE LOGITS
     outspoken
    1.36
    incón
    1.26
     วัน
    1.25
     BoxFit
    1.19
     all
    1.19
    حب
    1.18
    tanian
    1.16
     begin
    1.15
     носить
    1.14
    bcryptjs
    1.13
    Activations Density 0.011%

    No Known Activations