© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9259
    Prev
    Next
    INDEX
    Explanations

    sensory details and environmental nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     area
    0.59
    area
    0.52
    !
    0.52
     rower
    0.52
     Painting
    0.50
    !!!
    0.47
     Space
    0.47
    !!
    0.46
     fossa
    0.46
     region
    0.46
    POSITIVE LOGITS
     cuyas
    0.51
     गाड़ियों
    0.50
    konom
    0.50
    ד
    0.50
    હ
    0.48
     unapolog
    0.48
     борьбе
    0.47
     stubbornly
    0.47
    ന്മാ
    0.47
    acjach
    0.47
    Activations Density 0.209%

    No Known Activations