© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129964
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

    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
     dAtA
    -1.19
    rarr
    -1.00
    canActivate
    -0.98
    <()>
    -0.96
    ########
    -0.94
     pageContext
    -0.92
    chten
    -0.92
     ();
    -0.91
    らなかった
    -0.91
     dann
    -0.90
    POSITIVE LOGITS
    為に
    1.04
    方も
    1.02
    人も
    1.00
    際には
    0.96
     zowel
    0.96
     içeris
    0.95
    様な
    0.94
     also
    0.94
    Udo
    0.93
     vooral
    0.91
    Activations Density 0.001%

    No Known Activations