© 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. 215609
    Prev
    Next
    INDEX
    Explanations

    predicting costs or blocking

    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
     pene
    0.39
     lans
    0.39
    |
    0.37
     oficial
    0.37
    Beware
    0.36
     Berge
    0.36
     ment
    0.35
     fare
    0.35
     inadvertently
    0.34
     sanitized
    0.34
    POSITIVE LOGITS
    アイコン
    0.50
    为人
    0.47
     способности
    0.43
    }^{\#
    0.42
    DeathRecord
    0.42
    OrderFlight
    0.42
     отмети
    0.41
     ವಿಶೇಷ
    0.41
    ikus
    0.40
    ূহ
    0.40
    Activations Density 0.005%

    No Known Activations