© 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. 90925
    Prev
    Next
    INDEX
    Explanations

    all you need

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

    everything from

    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
     insgesamt
    0.48
     EVER
    0.44
    物体
    0.44
     motionProxy
    0.42
     hommage
    0.42
    物件
    0.41
     sebesar
    0.40
    唓
    0.40
     pacientes
    0.40
    Mileage
    0.40
    POSITIVE LOGITS
     imaginable
    0.65
     needed
    0.59
     conceivable
    0.58
     requisite
    0.54
     Needed
    0.54
     necessary
    0.53
     필요한
    0.52
     typical
    0.52
     необходимые
    0.52
     basics
    0.51
    Activations Density 0.106%

    No Known Activations