© 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. 12708
    Prev
    Next
    INDEX
    Explanations

    evaluation of

    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
     Doing
    -2.41
     You
    -2.36
     Anyone
    -2.27
    </b>
    -2.16
     Anything
    -2.14
     That
    -2.14
    3
    -2.11
     Ensuring
    -2.08
     Thus
    -2.06
     -
    -2.03
    POSITIVE LOGITS
    ಯ
    2.06
     llor
    2.06
     jajaja
    2.05
     للاس
    2.03
    鹩
    2.00
     TEACHERS
    1.95
     красивые
    1.94
     gracefully
    1.84
    書く
    1.83
     capitulo
    1.83
    Activations Density 0.105%

    No Known Activations