© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80164
    Prev
    Next
    INDEX
    Explanations

    ago

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     solns
    0.54
     atthakath
    0.46
     merits
    0.45
     scenarios
    0.45
     pptn
    0.45
     আস্থা
    0.45
     mannit
    0.45
    ቓ
    0.45
    securitycenter
    0.45
     ########.
    0.45
    POSITIVE LOGITS
    at
    0.56
    ü
    0.48
    ра
    0.46
    от
    0.45
    ğ
    0.45
    一
    0.44
    za
    0.43
    ügen
    0.43
    ici
    0.42
    га
    0.42
    Activations Density 0.008%

    No Known Activations