© 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-262K
    7. 135964
    Prev
    Next
    INDEX
    Explanations

    Fiber Type

    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
     entrepreneurs
    0.42
    ਟਰ
    0.41
     चाहिए
    0.41
    ನಾಡ
    0.40
     hyp
    0.39
    ᱧ
    0.39
     CHARACTER
    0.39
    꿩
    0.39
     terrorism
    0.38
     entrepreneur
    0.37
    POSITIVE LOGITS
     når
    0.40
     comenzó
    0.39
    gge
    0.39
     >
    0.38
    住了
    0.38
     stayed
    0.38
    象
    0.38
     didn
    0.37
     remained
    0.37
    olite
    0.37
    Activations Density 0.003%

    No Known Activations