© 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. 31-GEMMASCOPE-2-RES-65K
    7. 45076
    Prev
    Next
    INDEX
    Explanations

    circumcision

    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_31_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
     সঞ্জ
    0.49
    ﺳ
    0.44
    ಾರ
    0.41
    ্স
    0.40
    lceil
    0.40
     recycle
    0.40
     aceite
    0.39
    洎
    0.39
    循环
    0.39
    霜
    0.39
    POSITIVE LOGITS
     сведения
    0.46
     adherents
    0.46
     occupants
    0.46
     renderings
    0.46
    Washington
    0.45
    उप
    0.44
     hosts
    0.43
     Bellingham
    0.42
    View
    0.42
     Buccaneers
    0.42
    Activations Density 0.011%

    No Known Activations