© 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. 130765
    Prev
    Next
    INDEX
    Explanations

    been followed by past participle

    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
    </h3>
    -1.55
     freilich
    -1.50
    </h4>
    -1.44
    g
    -1.43
    u
    -1.42
    âge
    -1.42
     deshalb
    -1.42
    ’
    -1.41
    قلال
    -1.41
    =
    -1.37
    POSITIVE LOGITS
    ments
    1.48
    хани
    1.43
    dzić
    1.41
    tlement
    1.36
     oeil
    1.33
    餒
    1.30
     juſ
    1.30
     onore
    1.30
    //!
    1.30
    蕷
    1.27
    Activations Density 0.007%

    No Known Activations