© 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. 205040
    Prev
    Next
    INDEX
    Explanations

    medical advice or delay

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

    exam, step, drone

    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
     eine
    0.52
     zwei
    0.50
    Sea
    0.48
     اعتبار
    0.47
     Sea
    0.46
     두
    0.46
    也就是
    0.45
    siehe
    0.44
    तिया
    0.44
    riff
    0.43
    POSITIVE LOGITS
     bungalows
    0.50
     Rural
    0.49
     anticoag
    0.49
     rurales
    0.49
     hardwoods
    0.49
    ଳ
    0.47
     religions
    0.47
     rural
    0.46
    iracial
    0.46
     académicos
    0.46
    Activations Density 0.001%

    No Known Activations