© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 109324
    Prev
    Next
    INDEX
    Explanations

    £, parties, kubectl, insights, original

    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
    theoretic
    0.44
    hands
    0.39
    positroid
    0.39
    能力
    0.38
    라인
    0.38
    rowth
    0.38
    荼
    0.38
     காலநிலை
    0.37
    攸
    0.37
    balance
    0.36
    POSITIVE LOGITS
     kosong
    0.43
     abutting
    0.41
     большую
    0.40
     unchanged
    0.39
     ফজ
    0.39
     unst
    0.38
     iz
    0.37
     seated
    0.37
     outfile
    0.37
     en
    0.37
    Activations Density 0.000%

    No Known Activations