© 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. 34-GEMMASCOPE-RES-131K
    4. 90207
    Prev
    Next
    INDEX
    Explanations

    compatible and consistent states

    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
     Belleville
    -0.76
    цин
    -0.72
     TAI
    -0.69
    chiede
    -0.68
    ideon
    -0.68
    altezza
    -0.66
     régl
    -0.66
     obrig
    -0.66
     tưởng
    -0.65
    bech
    -0.64
    POSITIVE LOGITS
     compatible
    4.94
    compatible
    4.38
     Compatible
    4.28
    Compatible
    4.03
     consistent
    4.03
    consistent
    3.80
     compatibility
    3.47
     incompatible
    3.47
    Consistent
    3.39
     Consistent
    3.31
    Activations Density 0.107%

    No Known Activations