© 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. 200220
    Prev
    Next
    INDEX
    Explanations

    consent, comfort, objects

    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
     ಗೋ
    0.55
    юць
    0.48
    Ꮰ
    0.48
    יה
    0.47
    𝙪
    0.47
    ciende
    0.46
     erh
    0.45
     ਨਹੀਂ
    0.45
     כבר
    0.45
     ד
    0.45
    POSITIVE LOGITS
     Disney
    0.49
     plenary
    0.45
     consent
    0.44
     session
    0.41
    ,
    0.41
     Recap
    0.41
     Batman
    0.40
     Bishop
    0.39
     unintentionally
    0.39
     amended
    0.39
    Activations Density 0.004%

    No Known Activations