© 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. 128797
    Prev
    Next
    INDEX
    Explanations

    requests for help

    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
    :
    -1.92
     a
    -1.80
    --
    -1.66
     --
    -1.63
    を通して
    -1.55
    埝
    -1.52
    ൎ
    -1.52
     ...
    -1.51
     need
    -1.50
    をします
    -1.49
    POSITIVE LOGITS
    」、「
    1.82
    ……」
    1.80
    …」
    1.72
    रीदारी
    1.54
    shafen
    1.53
    方法
    1.51
    〃
    1.48
    capulco
    1.45
    Sabes
    1.45
    ❌
    1.44
    Activations Density 0.018%

    No Known Activations