© 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. 9322
    Prev
    Next
    INDEX
    Explanations

    news

    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
     to
    -1.16
    💃
    -1.03
    🏝
    -1.00
    _____________
    -0.99
    咂
    -0.98
     kasus
    -0.95
    EROS
    -0.95
    ACIO
    -0.95
    ӕ
    -0.94
    🙋
    -0.94
    POSITIVE LOGITS
     nhung
    1.10
    resulting
    1.06
    matorium
    1.04
    ൊ
    1.02
     xay
    1.00
    Kích
    1.00
    Algérie
    1.00
     değil
    0.98
     posiciones
    0.98
    implicitly
    0.98
    Activations Density 0.027%

    No Known Activations