© 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. 130475
    Prev
    Next
    INDEX
    Explanations

    separators and code structures

    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
     inox
    -1.80
     deko
    -1.77
    </
    -1.66
     kalender
    -1.65
     enceinte
    -1.63
     citroen
    -1.61
     auffi
    -1.59
    ate
    -1.59
     dacia
    -1.58
     ananas
    -1.55
    POSITIVE LOGITS
     with
    2.56
     if
    2.33
     from
    1.86
     we
    1.81
     through
    1.74
     as
    1.72
     If
    1.71
     during
    1.66
     for
    1.65
     when
    1.64
    Activations Density 0.009%

    No Known Activations