© 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. 10-GEMMASCOPE-RES-131K
    7. 58834
    Prev
    Next
    INDEX
    Explanations

    how much is

    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_10/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
     castellano
    -1.66
     españa
    -1.63
     they
    -1.62
    鲮
    -1.54
     belga
    -1.52
     lavable
    -1.52
     coreano
    -1.51
    蟊
    -1.51
     merveille
    -1.48
    栊
    -1.48
    POSITIVE LOGITS
     هذه
    1.67
    ?”
    1.66
     должны
    1.54
     هذا
    1.53
    This
    1.48
    焄
    1.48
    THIS
    1.47
    場合は
    1.41
     seperti
    1.39
    this
    1.38
    Activations Density 0.012%

    No Known Activations