© 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. 38327
    Prev
    Next
    INDEX
    Explanations

    rules, principles, and expectations

    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
    tasche
    -1.12
    不同的
    -1.08
     concernés
    -1.06
     Problemas
    -1.04
     passenden
    -1.03
     nějak
    -1.03
    ctivos
    -1.03
     olika
    -1.02
    鯢
    -1.00
    ならではの
    -0.99
    POSITIVE LOGITS
     both
    1.58
     our
    1.31
     who
    1.30
     nor
    1.29
     even
    1.27
     established
    1.23
     of
    1.23
     what
    1.18
     most
    1.17
     previous
    1.16
    Activations Density 0.017%

    No Known Activations