© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130925
    Prev
    Next
    INDEX
    Explanations

    probability questions about picking letters

    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
     on
    -1.39
     of
    -1.36
     in
    -1.35
     without
    -1.20
    تول
    -1.17
     has
    -1.16
     usually
    -1.16
     probably
    -1.15
     protège
    -1.13
    vriende
    -1.13
    POSITIVE LOGITS
     alcuni
    1.36
     alcune
    1.34
    ῖν
    1.29
     THOUGHT
    1.21
     pivotal
    1.20
    
    1.18
     BECAUSE
    1.18
    さり
    1.17
     ativar
    1.15
     condemns
    1.12
    Activations Density 0.001%

    No Known Activations