© 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. 34419
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables

    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
     précédentes
    -1.14
     précédents
    -1.06
     demandes
    -1.04
     icônes
    -1.02
     esegu
    -1.00
    anstalt
    -0.98
     gemak
    -0.96
     ポスター
    -0.96
    łoży
    -0.95
     vulgaires
    -0.95
    POSITIVE LOGITS
     and
    1.11
    傷害
    0.98
    合影
    0.94
    ultima
    0.93
    Lur
    0.92
     same
    0.91
     to
    0.90
     don
    0.88
     lastly
    0.88
     endorsements
    0.87
    Activations Density 0.001%

    No Known Activations