© 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. 235292
    Prev
    Next
    INDEX
    Explanations

    completely and"},royal thing"},concious level"}

    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
    Not in Any Lists

    No Comments

    Negative Logits
     πρώτη
    0.49
    螟
    0.48
    osaurs
    0.46
    ingan
    0.46
    iprop
    0.46
    aping
    0.45
     זו
    0.45
    zzz
    0.45
    asadd
    0.44
    VIII
    0.43
    POSITIVE LOGITS
     wavelength
    0.44
    ​
    0.43
    क्कर
    0.43
     kogu
    0.42
     ihrem
    0.42
     entièrement
    0.42
    ุล
    0.42
    साथ
    0.40
     completamente
    0.40
     bie
    0.40
    Activations Density 0.000%

    No Known Activations