© 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. 22-GEMMASCOPE-RES-131K
    7. 72330
    Prev
    Next
    INDEX
    Explanations

    code navigation `next`, `prev`, `find`

    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_22/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
     With
    -1.26
     Without
    -1.09
     this
    -1.05
     After
    -1.00
     One
    -0.98
     for
    -0.96
     so
    -0.96
    </strong>
    -0.95
    1
    -0.94
     If
    -0.94
    POSITIVE LOGITS
     others
    1.23
     zwi
    1.14
    friger
    1.06
     oogen
    1.00
    の中では
    1.00
    functioning
    0.99
     resten
    0.99
    ieval
    0.98
     functioning
    0.98
     jestem
    0.98
    Activations Density 0.003%

    No Known Activations