© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57167
    Prev
    Next
    INDEX
    Explanations

    previously unobserved or unknown

    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_34/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
     currently
    -1.59
     henceforth
    -1.58
     eventually
    -1.57
     lately
    -1.45
     soon
    -1.43
     subsequently
    -1.41
     presently
    -1.41
     earlier
    -1.39
     thereafter
    -1.38
     hereafter
    -1.35
    POSITIVE LOGITS
     mentioned
    1.33
     никогда
    1.30
    別の
    1.23
    কার
    1.16
     Ottobre
    1.13
    做过
    1.10
    Another
    1.09
     hanya
    1.09
    หน้านี้
    1.09
     used
    1.07
    Activations Density 0.053%

    No Known Activations