© 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. 92956
    Prev
    Next
    INDEX
    Explanations

    and followed by a word

    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
     especially
    -1.10
     Especially
    -1.09
     dessutom
    -1.02
    Especially
    -0.99
    特に
    -0.98
    icity
    -0.96
     inoltre
    -0.96
    ținut
    -0.95
    therners
    -0.95
    nī
    -0.93
    POSITIVE LOGITS
     it
    1.94
     wow
    1.45
     overall
    1.38
     WOW
    1.31
     found
    1.23
     impressed
    1.23
    wow
    1.19
     experience
    1.18
     although
    1.18
     regretted
    1.17
    Activations Density 0.022%

    No Known Activations