© 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. 172
    Prev
    Next
    INDEX
    Explanations

    disagreement and opinions

    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
     in
    -2.75
     by
    -2.63
     you
    -2.55
     of
    -2.34
     to
    -2.31
     with
    -2.25
     as
    -1.98
     especially
    -1.94
     including
    -1.89
     other
    -1.87
    POSITIVE LOGITS
     étan
    1.66
    šia
    1.50
     exemples
    1.48
    anyuan
    1.44
    他們
    1.43
    Angebot
    1.40
     réfrig
    1.39
     Paramètres
    1.39
    颓
    1.37
    .=
    1.36
    Activations Density 0.129%

    No Known Activations