© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75557
    Prev
    Next
    INDEX
    Explanations

    glyph, arche, hill, rock, hier

    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_34/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
     direct
    -0.82
    直
    -0.75
     Podcasts
    -0.75
     miracles
    -0.71
    คำ
    -0.70
     Chancen
    -0.69
    ophila
    -0.69
    Ψ
    -0.68
     miracle
    -0.68
     direkt
    -0.67
    POSITIVE LOGITS
     glyph
    2.41
    glyph
    1.97
     pet
    1.87
     Gly
    1.80
     gly
    1.80
    rogly
    1.76
    Glyph
    1.69
    ogly
    1.59
    gly
    1.48
    Gly
    1.45
    Activations Density 0.051%

    No Known Activations