© 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. 62825
    Prev
    Next
    INDEX
    Explanations

    HTML tags and links

    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
    şen
    -0.70
    іе
    -0.69
    ває
    -0.69
    xp
    -0.68
    интере
    -0.67
    폭
    -0.67
     showcase
    -0.66
    oux
    -0.65
     ListTile
    -0.65
    tily
    -0.65
    POSITIVE LOGITS
     link
    3.16
    link
    3.09
     linkage
    2.81
    Link
    2.73
     Link
    2.72
    LINK
    2.69
     links
    2.59
     LINK
    2.53
     linker
    2.47
     linking
    2.38
    Activations Density 0.097%

    No Known Activations