© 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. 78711
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinals

    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
     twenty
    -1.32
     Twenty
    -1.26
    Twenty
    -1.23
    Thirty
    -1.05
     Thirty
    -1.04
     vingt
    -0.94
     twentieth
    -0.93
    二十
    -0.93
     thirty
    -0.91
    twenty
    -0.91
    POSITIVE LOGITS
    twelve
    1.40
     eleven
    1.27
     ten
    1.26
     twelve
    1.24
     tenth
    1.20
     XII
    1.18
    eleven
    1.16
     twelfth
    1.13
     eleventh
    1.13
     Eleven
    1.12
    Activations Density 0.072%

    No Known Activations