© 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-65K
    7. 47576
    Prev
    Next
    INDEX
    Explanations

    Check, cleaned, hire

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    🇭
    0.44
    ®,
    0.42
     ®
    0.41
    ©
    0.41
    ※
    0.41
    Earl
    0.40
    Univers
    0.39
    Fork
    0.38
    🇹
    0.37
    Forward
    0.37
    POSITIVE LOGITS
     新品
    0.42
     Hamas
    0.41
    enye
    0.40
     ples
    0.40
    钚
    0.40
     Knesset
    0.39
     नए
    0.39
     antennes
    0.39
     XII
    0.38
     douze
    0.38
    Activations Density 0.001%

    No Known Activations