© 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. 130253
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

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

    harm underlying

    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
     देखती
    0.48
    եց
    0.48
    ሦ
    0.48
    mooth
    0.46
    ampton
    0.46
    wamy
    0.45
    intermedi
    0.45
    anın
    0.45
    ؤ
    0.45
    uiscono
    0.44
    POSITIVE LOGITS
    岩
    0.48
     oscillators
    0.46
    ActiveClass
    0.44
     program
    0.43
     Osc
    0.43
     oz
    0.43
     upload
    0.42
     garlic
    0.42
     anti
    0.41
     clip
    0.41
    Activations Density 0.001%

    No Known Activations