© 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. 34-GEMMASCOPE-RES-131K
    7. 77091
    Prev
    Next
    INDEX
    Explanations

    what follows sentence beginnings

    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
     др
    -1.16
     tüm
    -1.16
     IMHO
    -1.16
    Moreover
    -1.15
     GHG
    -1.14
     कई
    -1.12
     lze
    -1.09
    edded
    -1.09
     acaso
    -1.08
     всички
    -1.07
    POSITIVE LOGITS
     here
    2.02
     actually
    1.93
     gonna
    1.57
     tutaj
    1.51
    here
    1.44
     kind
    1.39
     pretty
    1.31
     guys
    1.31
    actually
    1.30
     somebody
    1.27
    Activations Density 0.018%

    No Known Activations