© 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. 67071
    Prev
    Next
    INDEX
    Explanations

    technical probes

    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
    ?”
    -2.97
    ro
    -2.75
    as
    -2.52
    is
    -2.45
    f
    -2.38
    ni
    -2.22
     honorable
    -2.22
    at
    -2.19
    va
    -2.19
     isn
    -2.16
    POSITIVE LOGITS
    饃
    2.38
     começaram
    2.34
    技术的
    2.30
    咛
    2.25
     fizeram
    2.23
    orsese
    2.23
     إعادة
    2.22
     efektif
    2.19
    뫼
    2.19
    ſtra
    2.17
    Activations Density 0.003%

    No Known Activations