© 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. 232576
    Prev
    Next
    INDEX
    Explanations

    statement of intent

    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
    つ
    0.53
    مة
    0.52
    の位置
    0.50
    スト
    0.49
    类
    0.49
    aves
    0.48
    evenly
    0.48
    ກ
    0.48
    ifts
    0.48
    στ
    0.46
    POSITIVE LOGITS
     dementia
    0.50
     Dementia
    0.47
     elle
    0.46
     enthusiast
    0.46
     net
    0.46
     December
    0.46
     mel
    0.44
     aus
    0.44
     lookout
    0.44
     lur
    0.43
    Activations Density 0.001%

    No Known Activations