© 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. 204692
    Prev
    Next
    INDEX
    Explanations

    responsive racing cars

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

    locations and events

    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
     తర్వాత
    0.44
    atia
    0.41
    伦
    0.41
    ชม
    0.41
    islava
    0.40
    zev
    0.39
    avos
    0.39
    <0xA4>
    0.39
    aille
    0.39
     размер
    0.39
    POSITIVE LOGITS
    ד
    0.49
     smiley
    0.46
     orbiting
    0.45
     situated
    0.45
     eastward
    0.45
     anecdotal
    0.44
    نی
    0.44
     sideways
    0.44
    Optical
    0.43
     agony
    0.43
    Activations Density 0.000%

    No Known Activations