© 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-16K
    7. 6558
    Prev
    Next
    INDEX
    Explanations

    identity and context

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     filosofía
    0.34
     estudiando
    0.32
     우리는
    0.31
    faceted
    0.31
    ა
    0.31
    💖
    0.31
    attacking
    0.31
    心を
    0.31
     visitare
    0.30
    💐
    0.30
    POSITIVE LOGITS
     faptul
    0.42
    i
    0.32
     khả
    0.32
     मौजूदगी
    0.32
     возможность
    0.31
    0.31
     அந்த
    0.30
     வகையில்
    0.30
    '
    0.29
    it
    0.29
    Activations Density 0.114%

    No Known Activations