© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40064
    Prev
    Next
    INDEX
    Explanations

    method is applied

    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
    𝛼
    -1.88
    _
    -1.73
    𝛽
    -1.66
    -1.59
    
    -1.59
    ではなく
    -1.58
     was
    -1.58
    thodoxy
    -1.57
    }}.
    -1.56
    }}{\
    -1.55
    POSITIVE LOGITS
     vaksin
    1.84
    🩹
    1.78
     effetto
    1.76
     vaksinasi
    1.69
     bénéfic
    1.67
    Siapa
    1.63
    Sometimes
    1.62
    Sejarah
    1.60
    Опис
    1.59
     мають
    1.59
    Activations Density 0.379%

    No Known Activations