© 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. 104661
    Prev
    Next
    INDEX
    Explanations

    software platforms and frameworks

    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
     '
    -1.27
     deaktivi
    -1.22
     "
    -1.20
     sachsen
    -1.19
     meint
    -1.16
     kuchen
    -1.11
     و
    -1.09
     lavadora
    -1.08
     mismos
    -1.06
     ใช้
    -1.05
    POSITIVE LOGITS
     merawat
    1.52
    Since
    1.45
    This
    1.43
    There
    1.41
    Because
    1.38
    Although
    1.34
    When
    1.34
     menangani
    1.30
     gezondheid
    1.28
    Being
    1.27
    Activations Density 0.000%

    No Known Activations