© 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. 41-GEMMASCOPE-2-RES-262K
    7. 101672
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
     uttered
    0.50
    ިއ
    0.47
    𒋗
    0.43
    edra
    0.43
    otry
    0.42
    তাম
    0.41
    etri
    0.40
    rafos
    0.40
    ября
    0.40
     రా
    0.39
    POSITIVE LOGITS
    amiliar
    0.39
    ที่ไม่
    0.39
     كث
    0.38
     токси
    0.36
    Vt
    0.35
     अपराध
    0.35
     opt
    0.34
    】-
    0.34
     quer
    0.33
     toxic
    0.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.