© 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. 22-GEMMASCOPE-RES-131K
    7. 15662
    Prev
    Next
    INDEX
    Explanations

    numerical times with am pm

    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_22/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
    -1.43
     but
    -1.35
     like
    -1.23
     q
    -1.15
     can
    -1.14
    <eos>
    -1.13
     x
    -1.12
    q
    -1.09
     K
    -1.09
     I
    -1.07
    POSITIVE LOGITS
     promesse
    1.30
     tristes
    1.24
    世界杯
    1.18
    läs
    1.16
     patrie
    1.14
     robuste
    1.13
    前言
    1.13
     seuil
    1.13
     coloriage
    1.12
     salaire
    1.10
    Activations Density 0.321%

    No Known Activations