© 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. 21148
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

    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
     If
    -2.47
     There
    -2.27
     whats
    -2.17
     ''
    -2.14
     -
    -2.11
     или
    -2.08
     has
    -2.08
     o
    -2.06
    There
    -2.02
    ')
    -2.00
    POSITIVE LOGITS
     própri
    2.67
    奩
    2.59
    several
    2.58
    糁
    2.58
     pérd
    2.56
    </i>
    2.56
     eſſ
    2.48
     semelh
    2.45
     indeks
    2.44
    醅
    2.39
    Activations Density 0.011%

    No Known Activations