© 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. 101739
    Prev
    Next
    INDEX
    Explanations

    case numbers and codes

    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
     have
    -2.33
     also
    -2.22
    )
    -2.13
     only
    -2.13
    }
    -2.09
     for
    -2.06
     mostly
    -2.02
     considered
    -1.89
    </h4>
    -1.86
    de
    -1.86
    POSITIVE LOGITS
    鸲
    2.06
     และ
    2.05
    ครื่อง
    1.75
    嫆
    1.71
    larda
    1.70
    🈷
    1.70
    bundet
    1.69
     drob
    1.66
    cinoma
    1.61
    訁
    1.61
    Activations Density 0.077%

    No Known Activations