© 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. 10-GEMMASCOPE-RES-131K
    7. 129798
    Prev
    Next
    INDEX
    Explanations

    describes perception or expectation

    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_10/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
    7
    -1.48
    ární
    -1.33
    ociação
    -1.33
    8
    -1.29
    Your
    -1.29
    cans
    -1.27
    6
    -1.27
    correct
    -1.25
     Hoffnung
    -1.24
     dibandingkan
    -1.24
    POSITIVE LOGITS
     nahezu
    1.27
     two
    1.26
     other
    1.25
     strung
    1.24
     three
    1.19
    ільки
    1.17
     from
    1.16
     alway
    1.16
     only
    1.14
    Btw
    1.12
    Activations Density 0.017%

    No Known Activations