© 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. 104244
    Prev
    Next
    INDEX
    Explanations

    that followed by a clause

    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
     certainly
    -1.34
     Certainly
    -1.27
     Perhaps
    -1.23
    chläge
    -1.23
     probably
    -1.16
     definitely
    -1.15
    などを
    -1.13
    を
    -1.12
     поскольку
    -1.11
     garner
    -1.10
    POSITIVE LOGITS
     you
    1.51
     montrant
    1.43
     كيفية
    1.41
    如此
    1.41
     we
    1.39
     malgré
    1.30
    で大
    1.27
    を選び
    1.27
     столь
    1.20
     böyle
    1.16
    Activations Density 0.014%

    No Known Activations