© 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. 255
    Prev
    Next
    INDEX
    Explanations

    year-over-year metrics

    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
     Sekarang
    -1.49
     Jér
    -1.43
    edoria
    -1.41
    icestershire
    -1.41
     OGSÅ
    -1.40
     sabar
    -1.40
     …”
    -1.38
     mno
    -1.38
    тарь
    -1.38
     ?
    -1.35
    POSITIVE LOGITS
    '
    2.30
     the
    1.54
    —
    1.53
     общего
    1.45
    ta
    1.41
    ra
    1.34
    ed
    1.34
    er
    1.34
    ca
    1.33
    ire
    1.30
    Activations Density 0.008%

    No Known Activations