© 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. 36887
    Prev
    Next
    INDEX
    Explanations

    princess, supported/disabled, go straight

    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
    Kd
    0.42
     Characters
    0.40
    Economics
    0.40
     isSignedIn
    0.39
     Chocolate
    0.39
    Charging
    0.38
    Wey
    0.37
     resided
    0.37
     \<
    0.37
    ța
    0.37
    POSITIVE LOGITS
     brutality
    0.40
    content
    0.40
    ready
    0.39
     physiological
    0.39
    luk
    0.39
     hypocrisy
    0.39
     Faites
    0.38
     بتكون
    0.38
    rops
    0.38
    voluntary
    0.38
    Activations Density 0.000%

    No Known Activations