© 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. 180411
    Prev
    Next
    INDEX
    Explanations

    comes with

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

    understand data structures

    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
    ியுடன்
    0.46
    வ்வாறு
    0.46
    forestation
    0.43
     pavements
    0.41
     verurs
    0.41
     vehicle
    0.41
    }}},
    0.40
    λογή
    0.40
    Forest
    0.40
     retorted
    0.40
    POSITIVE LOGITS
     élég
    0.53
    sht
    0.52
     शिम
    0.48
     कठिना
    0.47
     Sht
    0.47
     научной
    0.47
     ۴
    0.46
     구할
    0.46
     ۳
    0.46
    硞
    0.46
    Activations Density 0.001%

    No Known Activations