© 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. 6436
    Prev
    Next
    INDEX
    Explanations

    creating interfaces

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

    components and variations

    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
     mijn
    0.70
     hade
    0.64
     I
    0.56
     hebben
    0.56
    私は
    0.54
     was
    0.53
     had
    0.51
     waren
    0.51
     meinem
    0.51
     know
    0.50
    POSITIVE LOGITS
    OrCreate
    0.52
    栾
    0.48
     বরং
    0.48
     создает
    0.48
    শালী
    0.47
    Creates
    0.47
     每个
    0.45
    Creating
    0.44
     该
    0.44
     প্রতিটি
    0.44
    Activations Density 0.011%

    No Known Activations