© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70313
    Prev
    Next
    INDEX
    Explanations

    code generation and processing

    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
    荜
    -1.58
    于是
    -1.46
    うれ
    -1.44
     terutama
    -1.41
    iose
    -1.39
    兩種
    -1.38
    tabria
    -1.34
     cuadrada
    -1.34
     güne
    -1.33
    崛起
    -1.32
    POSITIVE LOGITS
     such
    1.57
     of
    1.52
     this
    1.49
    <td>
    1.45
     some
    1.41
     a
    1.33
     each
    1.30
     rosto
    1.29
     one
    1.27
     an
    1.26
    Activations Density 0.012%

    No Known Activations