© 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. 34242
    Prev
    Next
    INDEX
    Explanations

    Pokemon, Magic Marker Studios

    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
     and
    -1.28
     each
    -1.27
    return
    -1.09
     \&
    -1.02
    therefore
    -1.00
     therefore
    -1.00
    MLElement
    -0.98
     elements
    -0.97
    but
    -0.96
     thus
    -0.95
    POSITIVE LOGITS
     это
    1.26
     Tienen
    1.17
     bát
    1.17
     chaleureux
    1.05
     Actualmente
    1.05
     schneller
    1.04
     Pueden
    1.04
     omfatt
    1.01
    aryen
    1.01
    リット
    1.01
    Activations Density 0.065%

    No Known Activations