© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64140
    Prev
    Next
    INDEX
    Explanations

    positive energy

    np_acts-logits-general · gemini-2.5-flash-lite

    Nvidia, Beginner, Africa, Warrior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تش
    0.45
    NATO
    0.44
    ட்ரா
    0.42
     cafeteria
    0.42
     cafeter
    0.41
    꿋
    0.41
     ấm
    0.40
     épais
    0.40
    YR
    0.40
     vegetarian
    0.40
    POSITIVE LOGITS
     begins
    0.46
    线
    0.46
     रखें
    0.46
     Beginner
    0.46
     पुस्तकें
    0.45
     vorher
    0.45
    +-
    0.44
     Frequently
    0.44
     Tendulkar
    0.44
     начинает
    0.43
    Activations Density 0.000%

    No Known Activations