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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60604
    Prev
    Next
    INDEX
    Explanations

    It followed by a verb

    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
    ........
    -1.82
     to
    -1.78
    .......
    -1.69
    OLVED
    -1.68
    ocios
    -1.59
    ссий
    -1.55
    衛門
    -1.55
     dabar
    -1.53
    urgy
    -1.52
     iesp
    -1.52
    POSITIVE LOGITS
     it
    3.55
     of
    1.89
    它是
    1.69
    太多的
    1.67
     sabias
    1.67
    中です
    1.65
    はずです
    1.65
    にします
    1.55
     WHOLE
    1.52
     キーホルダー
    1.52
    Activations Density 0.096%

    No Known Activations