© 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. 133264
    Prev
    Next
    INDEX
    Explanations

    vowel teams, t-shirts, pre-clearance

    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
    ImmediateContext
    0.40
     hưởng
    0.38
    대는
    0.38
    ዋል።
    0.37
    clerotic
    0.37
     элект
    0.37
    Hua
    0.36
    耘
    0.36
     भा
    0.36
    وث
    0.36
    POSITIVE LOGITS
    ător
    0.44
     proves
    0.41
     today
    0.41
     requests
    0.41
     النهارده
    0.40
     casserole
    0.39
     turns
    0.38
     invariable
    0.38
     searches
    0.37
     proving
    0.37
    Activations Density 0.001%

    No Known Activations