© 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. 226998
    Prev
    Next
    INDEX
    Explanations

    Scooter bus travel

    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
     следующих
    0.50
     이상의
    0.49
    ホル
    0.48
    亠
    0.47
    各種
    0.47
    transmitted
    0.46
    以外の
    0.45
     transmits
    0.44
    たた
    0.44
    undi
    0.43
    POSITIVE LOGITS
     souten
    0.45
    🛴
    0.45
    ometown
    0.44
    eware
    0.43
     স্ট্যান্ড
    0.42
    iden
    0.42
     جھنڈ
    0.41
    bus
    0.41
     Scooter
    0.41
    footage
    0.40
    Activations Density 0.001%

    No Known Activations