© 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. 30996
    Prev
    Next
    INDEX
    Explanations

    column separators and structured data

    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
     an
    -1.19
     after
    -1.16
     eight
    -1.13
     getting
    -1.11
     any
    -1.11
     get
    -1.11
     for
    -1.10
     four
    -1.08
     (
    -1.07
     six
    -1.07
    POSITIVE LOGITS
    <th>
    1.37
    rather
    1.13
     !!!!!
    1.05
     minera
    1.02
     .........
    1.02
     remarkably
    1.01
     ____________
    1.01
     ___________
    1.01
     WITHIN
    1.00
    under
    0.99
    Activations Density 0.001%

    No Known Activations