© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 22105
    Prev
    Next
    INDEX
    Explanations

    duplicates, anonymous, journalism, cards

    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
    Not in Any Lists

    No Comments

    Negative Logits
     equivalence
    0.48
     equival
    0.43
    ницы
    0.42
    equival
    0.40
    丶
    0.39
    櫂
    0.39
    ksjon
    0.39
    adamia
    0.38
    বাদে
    0.38
    จักร
    0.38
    POSITIVE LOGITS
    }^{-\
    0.37
     responsible
    0.36
     CEO
    0.36
    ਖ਼
    0.35
     Responsible
    0.35
     Responsive
    0.35
     PU
    0.34
     cod
    0.34
    我对
    0.34
     Leute
    0.34
    Activations Density 0.000%

    No Known Activations