© 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. 193880
    Prev
    Next
    INDEX
    Explanations

    propaganda, blind, column, branching, weekend

    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
     팬
    0.41
     Tuk
    0.41
     फूलों
    0.39
     Tul
    0.39
     हेलो
    0.37
     rams
    0.37
     Cited
    0.37
     })}
    0.36
     пос
    0.36
     sited
    0.36
    POSITIVE LOGITS
    ినా
    0.46
     weighing
    0.39
    Dragging
    0.38
    obligation
    0.38
    NA
    0.37
    থর
    0.37
     oblig
    0.37
    Benef
    0.37
     nema
    0.36
    པ་
    0.36
    Activations Density 0.000%

    No Known Activations