© 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. 70860
    Prev
    Next
    INDEX
    Explanations

    legal and serious matters

    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
     kalender
    -1.27
     gård
    -1.27
     with
    -1.23
    ństw
    -1.13
    hitheater
    -1.12
     kommentar
    -1.12
    чник
    -1.12
     onsdag
    -1.11
     triko
    -1.11
    produzione
    -1.11
    POSITIVE LOGITS
     there
    1.71
     it
    1.54
    尤其
    1.29
     ふ
    1.27
     like
    1.23
     they
    1.20
    }$
    1.20
    like
    1.11
    ！】
    1.10
    폼
    1.09
    Activations Density 0.051%

    No Known Activations