© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130488
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and 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
    出色
    -1.35
     vaš
    -1.34
    וּ
    -1.24
    звичай
    -1.23
     takže
    -1.20
    เกี่ยวกับ
    -1.19
     širo
    -1.18
    ácti
    -1.18
     lecz
    -1.16
    aconda
    -1.16
    POSITIVE LOGITS
     we
    1.14
     Dansk
    1.09
    ֺ
    1.07
     roślin
    1.01
    бая
    0.98
    springen
    0.98
     hek
    0.98
     Gebruik
    0.96
    เดินทาง
    0.96
    然後
    0.96
    Activations Density 0.026%

    No Known Activations