© 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. 34-GEMMASCOPE-RES-131K
    7. 30317
    Prev
    Next
    INDEX
    Explanations

    units and measurements

    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_34/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
    えっ
    -1.36
    あぁ
    -1.29
    おそ
    -1.29
    壠
    -1.24
    にします
    -1.24
    もうすぐ
    -1.23
    本日の
    -1.21
    を行います
    -1.20
    に使用
    -1.17
    をします
    -1.16
    POSITIVE LOGITS
    짜
    1.27
    <bos>
    1.24
     version
    1.21
    児
    1.12
    ffiche
    1.05
    を
    1.05
    ŚĆ
    1.02
    diameter
    1.01
     Юрий
    1.00
    ombe
    1.00
    Activations Density 0.095%

    No Known Activations