© 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. 98365
    Prev
    Next
    INDEX
    Explanations

    other articles

    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
     réessayer
    -1.28
     cáp
    -1.26
    ᾿
    -1.22
     stieg
    -1.22
     QLabel
    -1.20
    Istorija
    -1.20
    ⎩
    -1.20
    ofre
    -1.17
    ceptors
    -1.16
     depois
    -1.16
    POSITIVE LOGITS
     these
    2.38
     other
    2.11
     many
    1.43
     various
    1.34
    Other
    1.27
    these
    1.27
     only
    1.24
     esempi
    1.22
     those
    1.20
     some
    1.19
    Activations Density 0.049%

    No Known Activations