© 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. 138334
    Prev
    Next
    INDEX
    Explanations

    identifying specific terms

    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
    猀
    0.45
    ми
    0.43
    ти
    0.43
    ের
    0.43
    ྵ
    0.43
    ς
    0.42
    árez
    0.42
    дит
    0.41
    ៤
    0.41
    diği
    0.40
    POSITIVE LOGITS
     from
    0.55
     up
    0.55
     handy
    0.55
     innovation
    0.54
    Up
    0.53
     love
    0.52
     innovations
    0.52
     optimism
    0.52
     handbag
    0.50
     very
    0.50
    Activations Density 0.005%

    No Known Activations