© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19460
    Prev
    Next
    INDEX
    Explanations

    priority, goal, theme, concern, routine

    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
    dzić
    -1.32
    Cinem
    -1.26
     بعض
    -1.21
    .*;
    -1.20
    Ը
    -1.16
     دیگر
    -1.16
    SOME
    -1.15
     einige
    -1.14
    ți
    -1.13
     zwischen
    -1.13
    POSITIVE LOGITS
     both
    1.53
    してほしい
    1.42
    os
    1.38
     precisely
    1.34
     imagenes
    1.29
    efore
    1.28
     municipios
    1.28
     every
    1.27
    してみて
    1.24
     kufanya
    1.24
    Activations Density 0.117%

    No Known Activations