© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103959
    Prev
    Next
    INDEX
    Explanations

    driven or oriented

    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
    杈
    -1.12
     verschiedene
    -1.09
    borderSide
    -1.07
    范围内
    -1.06
    localObject
    -1.06
     cioc
    -1.05
    ± 
    -1.04
    </tfoot>
    -1.04
    ?"
    -1.03
    rası
    -1.03
    POSITIVE LOGITS
     rather
    1.29
    而不是
    1.29
     plutôt
    1.23
     DATOS
    1.18
    比起
    1.17
     більш
    1.17
    ccion
    1.14
    donc
    1.13
     живет
    1.13
    перь
    1.13
    Activations Density 0.108%

    No Known Activations