© 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. 48484
    Prev
    Next
    INDEX
    Explanations

    MA crosses, quick cuts, financial limits

    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
    ಃ
    0.46
    ah
    0.46
    hu
    0.45
    ologie
    0.45
    eli
    0.45
    ъл
    0.45
    ה
    0.45
    ذج
    0.44
    ̞
    0.44
    い
    0.44
    POSITIVE LOGITS
     valu
    0.48
     smaller
    0.46
     insuff
    0.46
     lessor
    0.44
     maximum
    0.43
     accessibility
    0.42
     access
    0.41
     minimum
    0.41
     wartości
    0.41
     Mijn
    0.41
    Activations Density 0.017%

    No Known Activations