© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36409
    Prev
    Next
    INDEX
    Explanations

    positional digits

    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_22/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
     alluring
    -0.88
     ſen
    -0.86
     OFFERS
    -0.85
    abancı
    -0.84
    imin
    -0.84
     sorti
    -0.83
     Dinas
    -0.83
     лето
    -0.82
     таких
    -0.82
     fid
    -0.82
    POSITIVE LOGITS
     again
    1.45
    再び
    1.19
     opnieuw
    1.05
     دوباره
    1.01
     and
    1.00
     nuovamente
    0.99
    再度
    0.91
    𓂃
    0.91
     kembali
    0.85
    âmetros
    0.82
    Activations Density 0.009%

    No Known Activations