© 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. 123164
    Prev
    Next
    INDEX
    Explanations

    fetishistic, atropine, computer, marionette, cooling

    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
    sí
    0.51
    ník
    0.49
    łek
    0.49
     چاہی
    0.47
    出来
    0.47
    ݨ
    0.46
    cích
    0.44
     Seab
    0.44
    ⚛
    0.43
    㪇
    0.43
    POSITIVE LOGITS
     amps
    0.51
     criticizing
    0.43
     amyg
    0.42
     विशेषज्ञों
    0.41
    자인
    0.41
     பாஜக
    0.39
     ethically
    0.39
    ologiche
    0.39
    ioribus
    0.39
     analyzers
    0.39
    Activations Density 0.007%

    No Known Activations