© 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. 31-GEMMASCOPE-2-RES-262K
    7. 76153
    Prev
    Next
    INDEX
    Explanations

    Ukraine, safety, keys, dark jokes

    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_31_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
     kombin
    0.51
     llegaron
    0.48
     elegante
    0.48
     elektrische
    0.48
    ###########
    0.45
    ँची
    0.44
     různ
    0.43
     schafft
    0.43
     immersive
    0.43
     Hanya
    0.43
    POSITIVE LOGITS
    н
    0.48
     offenders
    0.48
     violators
    0.48
     тех
    0.46
    у
    0.45
     оружи
    0.44
     wounds
    0.44
     negligent
    0.44
    atation
    0.44
     क्षेत्रों
    0.43
    Activations Density 0.016%

    No Known Activations