© 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. 38884
    Prev
    Next
    INDEX
    Explanations

    tensor shape

    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
     hinder
    -1.88
     コス
    -1.52
     terlalu
    -1.52
    儇
    -1.45
     kein
    -1.45
    ௦
    -1.44
     zobac
    -1.39
    werden
    -1.39
    暘
    -1.38
     ebenso
    -1.36
    POSITIVE LOGITS
     they
    1.56
    𝓁
    1.41
     في
    1.41
    t
    1.39
    <bos>
    1.38
    ?
    1.38
     vertre
    1.38
     remaining
    1.33
    şağı
    1.32
     It
    1.31
    Activations Density 0.002%

    No Known Activations