© 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. 22-GEMMASCOPE-RES-131K
    7. 38347
    Prev
    Next
    INDEX
    Explanations

    validity checks and greetings

    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
    rierten
    -1.05
     赤ちゃん
    -0.93
    ———-
    -0.91
    Πηγή
    -0.87
    Danger
    -0.85
    CloseOperation
    -0.85
    yled
    -0.84
     стр
    -0.84
    ЗЫ
    -0.84
    _^
    -0.83
    POSITIVE LOGITS
     range
    1.12
    Reactions
    0.89
     shores
    0.86
     if
    0.84
    姿を
    0.84
    IsValid
    0.83
    cookieParser
    0.82
     people
    0.81
    if
    0.81
     rage
    0.80
    Activations Density 0.010%

    No Known Activations