© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113384
    Prev
    Next
    INDEX
    Explanations

    metamorphosis into butterflies

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

    precursor to, debating the, fancy cheese

    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
    र्ण
    0.54
     moistened
    0.54
    িশীল
    0.53
    ΑΣ
    0.52
    ्योपै
    0.50
     humides
    0.49
    咿
    0.48
    ని
    0.48
    डीए
    0.47
     ambientes
    0.47
    POSITIVE LOGITS
    number
    0.51
    an
    0.51
    another
    0.49
    next
    0.49
    số
    0.49
    trunc
    0.47
    wellness
    0.47
    t
    0.47
    deg
    0.46
    ént
    0.46
    Activations Density 0.000%

    No Known Activations