© 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. 73975
    Prev
    Next
    INDEX
    Explanations

    movement

    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
     
    -1.70
    _
    -1.59
     sumptuous
    -1.55
     crucial
    -1.48
     внутрен
    -1.45
    a
    -1.45
     blatant
    -1.45
     I
    -1.43
     hefty
    -1.41
     hierzu
    -1.40
    POSITIVE LOGITS
     the
    2.73
     of
    1.77
     their
    1.73
     with
    1.65
     from
    1.58
     during
    1.57
     drame
    1.56
     akad
    1.50
     through
    1.50
     before
    1.49
    Activations Density 0.029%

    No Known Activations