© 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. 10-GEMMASCOPE-RES-131K
    4. 123821
    Prev
    Next
    INDEX
    Explanations

    but

    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_10/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
     and
    -1.84
    これらの
    -1.69
    These
    -1.62
     these
    -1.46
     a
    -1.46
    :
    -1.35
    ok
    -1.33
     also
    -1.30
    Being
    -1.27
     probably
    -1.26
    POSITIVE LOGITS
    
    1.55
    প্র
    1.37
    critto
    1.36
     utilizando
    1.34
     nowy
    1.34
     Универ
    1.30
    tahan
    1.29
     pierwszy
    1.28
     informaron
    1.27
     pokoj
    1.26
    Activations Density 0.135%

    No Known Activations