© 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. 90801
    Prev
    Next
    INDEX
    Explanations

    even expert child started

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

    how something works

    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
    <0x0D>
    0.52
    engono
    0.47
     আশ্চর্যজনক
    0.46
    data
    0.45
     insanely
    0.44
    wa
    0.44
     unimaginable
    0.44
     तुलना
    0.43
    </h2>
    0.43
    fake
    0.43
    POSITIVE LOGITS
     buildFor
    0.51
     jeżeli
    0.50
     подойдет
    0.50
     systeem
    0.48
     tubercul
    0.46
    适用于
    0.44
    𒊏
    0.43
     змо
    0.43
     급
    0.42
     erős
    0.42
    Activations Density 0.001%

    No Known Activations