© 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. 49442
    Prev
    Next
    INDEX
    Explanations

    utility helper function calls

    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
     that
    -1.86
     on
    -1.46
    !!!!
    -1.32
     this
    -1.30
    !!
    -1.29
     when
    -1.28
    !!!
    -1.28
     for
    -1.27
    !!!!!
    -1.23
     any
    -1.23
    POSITIVE LOGITS
     stiller
    1.30
    ův
    1.30
     eral
    1.29
    歺
    1.27
     firſt
    1.27
     monstru
    1.23
     kado
    1.23
     ROBERT
    1.23
    注意事
    1.21
     juſt
    1.21
    Activations Density 0.010%

    No Known Activations