© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 2958
    Prev
    Next
    INDEX
    Explanations

    URL and news sources

    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
    Not in Any Lists

    No Comments

    Negative Logits
     sanguí
    0.29
    ികിത്സ
    0.25
    observatoire
    0.25
    隂
    0.23
     خون
    0.23
     suppuration
    0.23
    狲
    0.23
    铒
    0.22
    燹
    0.22
     jornalista
    0.22
    POSITIVE LOGITS
     science
    0.29
     Science
    0.26
     reported
    0.25
     world
    0.24
     individuals
    0.24
     Tech
    0.23
     business
    0.23
     standards
    0.22
     history
    0.22
     thought
    0.22
    Activations Density 0.006%

    No Known Activations