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

    Neuronpedia

    Jacobian LensNEW
    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. 25376
    Prev
    Next
    INDEX
    Explanations

    abuse, marketing, america

    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
    ia
    0.49
    les
    0.45
     okam
    0.42
     Key
    0.40
    8
    0.39
    ider
    0.39
     impossible
    0.39
     illa
    0.39
    č
    0.38
    us
    0.38
    POSITIVE LOGITS
    人民共和国
    0.48
    襷
    0.46
     таксама
    0.44
    ведении
    0.44
    ционер
    0.43
     vengo
    0.43
     chaired
    0.43
    <unused2175>
    0.43
     आपराधिक
    0.43
    瞽
    0.43
    Activations Density 0.013%

    No Known Activations