© 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. 22-GEMMASCOPE-RES-131K
    7. 95837
    Prev
    Next
    INDEX
    Explanations

    differences in quantities or rankings

    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
    QUADS
    -0.86
    softmax
    -0.85
     mev
    -0.84
    浃
    -0.82
    DeleteBehavior
    -0.82
     ingeniero
    -0.82
    ποίη
    -0.82
    Мекси
    -0.80
    funktion
    -0.80
    ategori
    -0.80
    POSITIVE LOGITS
     légèrement
    0.92
     close
    0.88
     slightly
    0.83
    īgā
    0.82
     overall
    0.82
     dadurch
    0.82
    paralleled
    0.77
    ficult
    0.77
     ligeramente
    0.77
     narrowly
    0.75
    Activations Density 0.039%

    No Known Activations