© 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. 13105
    Prev
    Next
    INDEX
    Explanations

    purpose or benefit

    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
     the
    -1.83
    ଞ
    -1.66
    ありがたい
    -1.66
    句話
    -1.65
    Ꮞ
    -1.63
     factors
    -1.63
    Fär
    -1.63
    樒
    -1.59
    }
    -1.59
    並且
    -1.59
    POSITIVE LOGITS
    uarts
    1.82
    螃
    1.80
    那些
    1.76
    犛
    1.71
     тех
    1.71
    weetened
    1.69
    Cartney
    1.69
    estacks
    1.66
    PageFactory
    1.66
     Teléfono
    1.66
    Activations Density 0.047%

    No Known Activations