© 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. 235250
    Prev
    Next
    INDEX
    Explanations

    editorial team

    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
    dessus
    0.52
     እንቅ
    0.51
    ън
    0.50
    ър
    0.49
    ъл
    0.47
    ्रपान
    0.46
    ི
    0.46
    unna
    0.45
    asen
    0.45
    <0x10>
    0.44
    POSITIVE LOGITS
    https
    0.53
     HK
    0.52
    t
    0.52
     Sek
    0.50
     in
    0.49
     yuk
    0.48
     Wired
    0.48
     böl
    0.47
     Montana
    0.47
     Red
    0.46
    Activations Density 0.000%

    No Known Activations