© 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. 128347
    Prev
    Next
    INDEX
    Explanations

    html tags and attributes

    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
     such
    -1.05
     všech
    -1.00
     kristal
    -0.97
     každý
    -0.97
    odotus
    -0.93
     belki
    -0.93
    gesteld
    -0.90
     différents
    -0.90
     désormais
    -0.89
     kutu
    -0.89
    POSITIVE LOGITS
    Though
    1.08
    Even
    1.07
    While
    1.00
    Bolt
    0.98
     Even
    0.97
    .
    0.96
     at
    0.94
     requires
    0.94
    They
    0.92
     ellos
    0.91
    Activations Density 0.000%

    No Known Activations