© 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. 85263
    Prev
    Next
    INDEX
    Explanations

    Filipino, Hebrew, Slavic, and Irish fragments

    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
    <bos>
    -1.71
    ॲ
    -1.65
     sostener
    -1.52
    以前的
    -1.51
    感じで
    -1.50
     ralenti
    -1.50
     renfor
    -1.48
     Usar
    -1.48
     pensar
    -1.42
    /
    -1.41
    POSITIVE LOGITS
     for
    2.02
     into
    1.87
    ensory
    1.70
     forKey
    1.64
     on
    1.63
    cting
    1.61
    umers
    1.56
     also
    1.55
    тура
    1.53
    nables
    1.50
    Activations Density 0.014%

    No Known Activations