© 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. 235727
    Prev
    Next
    INDEX
    Explanations

    growth, emergence, and state transitions

    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
     Delt
    0.47
     △
    0.45
     diffraction
    0.44
     Eighth
    0.44
     Inject
    0.44
     Sc
    0.44
     Juillet
    0.44
     Rhin
    0.43
     النت
    0.43
     계
    0.43
    POSITIVE LOGITS
    如今
    0.59
    日益
    0.47
    SALE
    0.46
     же
    0.46
    虽然
    0.46
    ’
    0.45
    strates
    0.45
    })-
    0.45
    middels
    0.45
    आपने
    0.44
    Activations Density 0.001%

    No Known Activations