© 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. 31637
    Prev
    Next
    INDEX
    Explanations

    introductions, lists, or attributes

    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
     astu
    -0.84
    ENVIRONMENTAL
    -0.82
    ждает
    -0.82
    ridgeshire
    -0.82
     INSTALLATION
    -0.81
    缜
    -0.81
    づけ
    -0.80
     miljö
    -0.80
     Gegenteil
    -0.80
    🦉
    -0.79
    POSITIVE LOGITS
     class
    0.82
     transform
    0.79
     Transforming
    0.77
    함
    0.75
    transform
    0.74
     "
    0.71
     transformation
    0.70
    hero
    0.69
     genoemd
    0.68
    血
    0.68
    Activations Density 0.007%

    No Known Activations