© 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. 45268
    Prev
    Next
    INDEX
    Explanations

    haiku prompts

    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
    지의
    0.44
    Pi
    0.41
     vesicle
    0.41
    Q
    0.41
     excitatory
    0.40
    지
    0.40
    二
    0.40
    돔
    0.40
    큐
    0.40
    MM
    0.40
    POSITIVE LOGITS
     Aug
    0.46
     کمپیوٹر
    0.43
     Nov
    0.42
     trademark
    0.42
     які
    0.41
     कंप्यूटर
    0.41
     hvis
    0.40
     terzo
    0.40
     шеран
    0.40
     amelyek
    0.40
    Activations Density 0.013%

    No Known Activations