© 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. 39295
    Prev
    Next
    INDEX
    Explanations

    may be required or deemed

    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
     entren
    -1.68
     tels
    -1.56
    gives
    -1.56
     accelerates
    -1.52
    vosť
    -1.50
    somebody
    -1.49
     voilà
    -1.48
     desn
    -1.48
     appris
    -1.48
     extingu
    -1.48
    POSITIVE LOGITS
     they
    2.23
     for
    2.09
     with
    2.00
     or
    1.98
     from
    1.90
     that
    1.79
     them
    1.79
     first
    1.69
     where
    1.67
     by
    1.63
    Activations Density 0.008%

    No Known Activations