© 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. 142778
    Prev
    Next
    INDEX
    Explanations

    introducing conditional clauses

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

    introducing conditional clauses

    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
     rupture
    0.51
     fatality
    0.50
     renter
    0.50
    ]*
    0.49
     deadlock
    0.48
     solubility
    0.47
     stalemate
    0.47
     walkway
    0.46
     voyages
    0.46
     for
    0.45
    POSITIVE LOGITS
     пыта
    0.52
     Armen
    0.46
     Dienste
    0.45
     Deshalb
    0.44
     wszel
    0.44
    每次
    0.44
     номера
    0.42
     Acerca
    0.42
    雱
    0.42
     हमेशा
    0.42
    Activations Density 0.047%

    No Known Activations