© 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. 85333
    Prev
    Next
    INDEX
    Explanations

    preposition to conjunction

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

    potential effects, generation, desensitization, PRs, terminal

    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
    룺
    0.51
    𝓃
    0.49
     suces
    0.48
     RECOMM
    0.48
    鑒
    0.48
     décisions
    0.47
    訌
    0.47
    シュ
    0.46
     Rek
    0.46
    nienia
    0.46
    POSITIVE LOGITS
    érables
    0.55
    ang
    0.51
    Azure
    0.48
     วัน
    0.47
    Andrew
    0.46
     грудня
    0.45
    elle
    0.43
    etch
    0.42
    eryl
    0.42
    ib
    0.42
    Activations Density 0.000%

    No Known Activations