© 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. 118083
    Prev
    Next
    INDEX
    Explanations

    contact information, legal terms, or technical details

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

    feeding bottle

    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
     médian
    0.62
     沒有
    0.54
     μουσ
    0.52
     ժ
    0.51
     изобра
    0.51
     soutenir
    0.51
     hled
    0.51
    𝐬
    0.51
    通话
    0.50
    ísica
    0.50
    POSITIVE LOGITS
    ulating
    0.49
     rituals
    0.48
     ritual
    0.47
     broth
    0.47
     resale
    0.47
    OGR
    0.46
     desert
    0.45
     jogging
    0.45
    ></
    0.44
     tattoo
    0.44
    Activations Density 0.000%

    No Known Activations