© 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. 73585
    Prev
    Next
    INDEX
    Explanations

    /thirdcircuit_

    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
     In
    -1.18
     even
    -1.12
     United
    -1.11
     they
    -1.11
     For
    -1.10
     have
    -1.06
     None
    -1.06
     America
    -1.04
     both
    -1.04
     should
    -1.04
    POSITIVE LOGITS
     Siapa
    1.20
     achie
    1.19
    jäh
    1.14
    Verbindung
    1.13
     שלנו
    1.13
    Keterangan
    1.12
     cipolla
    1.10
     doigts
    1.10
    Teilen
    1.09
     nameof
    1.08
    Activations Density 0.001%

    No Known Activations