© 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. 9252
    Prev
    Next
    INDEX
    Explanations

    breakdown and categorization

    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
     också
    0.36
     bajos
    0.36
     також
    0.36
     бана
    0.36
    אם
    0.34
     คะแนน
    0.34
     أيضا
    0.34
     সামান্য
    0.33
    ᅩ
    0.33
     benefícios
    0.32
    POSITIVE LOGITS
    guide
    0.42
     discusses
    0.39
     विवे
    0.39
     explores
    0.39
     विश्लेषण
    0.38
     จัด
    0.38
    ​,
    0.38
    >,
    0.38
    Guide
    0.37
     explore
    0.37
    Activations Density 0.356%

    No Known Activations