© 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. 9412
    Prev
    Next
    INDEX
    Explanations

    counts of subjects or samples

    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
     "
    -0.99
    гона
    -0.97
     keduanya
    -0.94
     really
    -0.92
     to
    -0.92
     ambos
    -0.91
     constantly
    -0.91
     keep
    -0.91
     „
    -0.88
     continuously
    -0.87
    POSITIVE LOGITS
     disponível
    1.11
     चुन
    1.09
     Möglich
    1.07
     achats
    1.05
     éché
    1.04
     SAYS
    1.02
     broader
    1.02
     GUARANTEE
    1.01
    ťa
    1.00
     EXIST
    1.00
    Activations Density 0.028%

    No Known Activations