© 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. 117208
    Prev
    Next
    INDEX
    Explanations

    mighty and almighty

    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
    since
    -0.79
    LLYWOOD
    -0.79
     limelight
    -0.78
     millennium
    -0.77
     geology
    -0.76
    rician
    -0.75
    Butter
    -0.75
    遗传
    -0.74
     столи
    -0.74
     Zähne
    -0.74
    POSITIVE LOGITS
     oaks
    1.15
     Mouse
    1.11
    Mouse
    0.97
    MOUSE
    0.94
    Fine
    0.92
     fine
    0.87
     impressive
    0.85
     eraser
    0.85
     MOUSE
    0.84
     puissance
    0.80
    Activations Density 0.014%

    No Known Activations