© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32899
    Prev
    Next
    INDEX
    Explanations

    Yup, Yes, Yep

    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
     and
    -1.74
     which
    -1.61
     but
    -1.43
     Nope
    -1.20
     yeah
    -1.14
     YEAH
    -1.10
     nope
    -1.02
     what
    -1.01
     Yeah
    -1.00
     how
    -0.95
    POSITIVE LOGITS
     you
    1.81
     folks
    1.42
    没错
    1.23
     Virginia
    1.20
     plural
    1.17
     ladies
    1.16
    Virginia
    1.15
     it
    1.13
     आपको
    1.09
     mesmo
    1.06
    Activations Density 0.015%

    No Known Activations