© 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. 27966
    Prev
    Next
    INDEX
    Explanations

    reporting or reflecting unusual 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_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
    AntiForgeryToken
    -0.99
    proved
    -0.95
    ATED
    -0.91
    actose
    -0.86
     accepte
    -0.85
    ちゃんと
    -0.84
     ausgeführt
    -0.84
    ші
    -0.83
     urgente
    -0.83
     fuir
    -0.83
    POSITIVE LOGITS
     reporting
    1.31
     because
    1.19
    false
    1.10
     reflects
    1.05
     report
    1.03
     when
    0.99
     appear
    0.97
    because
    0.96
     reports
    0.95
     artificially
    0.94
    Activations Density 0.100%

    No Known Activations