© 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. 71474
    Prev
    Next
    INDEX
    Explanations

    Goshen County

    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
    Unlike
    -1.84
    Even
    -1.80
    These
    -1.77
    このような
    -1.77
    Despite
    -1.76
    Our
    -1.73
    <h2>
    -1.72
    Several
    -1.69
    When
    -1.68
    During
    -1.67
    POSITIVE LOGITS
     a
    2.41
     to
    2.11
    ToMany
    1.84
    荭
    1.80
     andere
    1.74
    сль
    1.65
    ForRow
    1.65
     recibe
    1.63
    PointerException
    1.59
    omorphisms
    1.58
    Activations Density 0.186%

    No Known Activations