© 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. 205731
    Prev
    Next
    INDEX
    Explanations

    waves, legendary, meat, loving, rule, political, relation

    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
     protrusion
    0.42
     protrusions
    0.42
     hugged
    0.42
    =""><
    0.41
    延伸
    0.40
    vaccinated
    0.40
     quitting
    0.40
     দৃষ্টি
    0.39
    κού
    0.39
    系
    0.38
    POSITIVE LOGITS
     Dhan
    0.39
    ICE
    0.37
     Umgebung
    0.37
    King
    0.37
     tecnica
    0.37
     Somm
    0.37
    NumberOperation
    0.36
     Du
    0.36
     Duct
    0.36
     মহাশয়
    0.35
    Activations Density 0.001%

    No Known Activations