© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166580
    Prev
    Next
    INDEX
    Explanations

    bidding, tears, heaven, afterward, under, springs, outside

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

    not ... the, a, create

    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
    Negative Logits
     Vehicles
    0.46
     Denis
    0.44
    므로
    0.44
    ğine
    0.44
     )
    0.43
    BRO
    0.42
    DV
    0.42
    】
    0.42
    Ди
    0.42
    ریر
    0.42
    POSITIVE LOGITS
     dismal
    0.49
     प्रेरणात्मक
    0.49
    <0x84>
    0.48
     जीते
    0.47
     सच्चाई
    0.47
    floral
    0.46
     экологи
    0.45
     rotting
    0.45
    what
    0.45
     जोरदार
    0.45
    Activations Density 0.002%

    No Known Activations