© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36848
    Prev
    Next
    INDEX
    Explanations

    widely used by many

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    context
    0.43
    cemment
    0.42
    場合があります
    0.42
     সামনে
    0.38
     potp
    0.38
    Always
    0.38
     hazır
    0.38
    ᅣ
    0.38
     zainteres
    0.37
     subgoal
    0.37
    POSITIVE LOGITS
     thousands
    0.79
     Thousands
    0.79
     countless
    0.79
     millions
    0.74
     endorsed
    0.70
     लाखों
    0.67
     milhares
    0.66
    thousands
    0.66
     hundreds
    0.65
     worldwide
    0.65
    Activations Density 0.006%

    No Known Activations