© 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. 34-GEMMASCOPE-RES-131K
    7. 117388
    Prev
    Next
    INDEX
    Explanations

    the matter

    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_34/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
    الات
    -0.81
     *}
    -0.79
     *}$
    -0.75
    varlak
    -0.74
    Themes
    -0.74
     mouseY
    -0.72
    erer
    -0.70
    ود
    -0.70
    чом
    -0.70
     Ry
    -0.69
    POSITIVE LOGITS
     matter
    6.75
    matter
    4.91
     matters
    4.66
    Matter
    3.97
     Matter
    3.70
     MATTER
    3.66
    matters
    3.34
     Matters
    3.05
     issue
    3.03
    Matters
    3.00
    Activations Density 0.054%

    No Known Activations