© 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. 111110
    Prev
    Next
    INDEX
    Explanations

    likely that or you

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

    command of the past hour

    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
    ulates
    0.49
    ВС
    0.46
    (__
    0.45
    DataAnnotations
    0.44
    ologically
    0.44
    ulated
    0.44
     sticking
    0.43
    inating
    0.43
    ↕
    0.43
    ages
    0.43
    POSITIVE LOGITS
     Mgr
    0.53
     appel
    0.50
    炕
    0.49
     veliki
    0.49
     father
    0.47
     руб
    0.46
     HOT
    0.46
    nyk
    0.46
     Planet
    0.45
     planet
    0.45
    Activations Density 0.000%

    No Known Activations