© 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. 54915
    Prev
    Next
    INDEX
    Explanations

    voluntarily leaving, not physical blockage

    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
    RequestParam
    0.39
     consentimiento
    0.39
     způsob
    0.39
    cyclo
    0.39
     sockfd
    0.38
    িল্লা
    0.37
    교
    0.37
     spôsob
    0.37
    ذ
    0.36
    ྷ
    0.36
    POSITIVE LOGITS
     Meridian
    0.46
     MER
    0.44
     Eden
    0.42
     CT
    0.41
     MERC
    0.41
    Merc
    0.40
     beh
    0.40
     Balanced
    0.40
     Merc
    0.40
     STR
    0.39
    Activations Density 0.001%

    No Known Activations