© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10092
    Prev
    Next
    INDEX
    Explanations

    duration and time units

    np_acts-logits-general · gemini-2.5-flash-lite

    Protein sources: Protein Sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ›
    0.47
    f
    0.46
    ‚
    0.46
     Appeals
    0.44
     লোককে
    0.43
    fda
    0.43
    v
    0.43
    いを
    0.42
    e
    0.42
     বৃ
    0.42
    POSITIVE LOGITS
     sommes
    0.60
     entsprechende
    0.54
     köş
    0.52
     নীতি
    0.50
     konten
    0.50
     longueur
    0.49
     بروز
    0.49
     নীতির
    0.48
     esperamos
    0.48
     humaines
    0.48
    Activations Density 0.000%

    No Known Activations