© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 44831
    Prev
    Next
    INDEX
    Explanations

    tides, crow, check

    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
    ipp
    0.45
     prospective
    0.42
     নির্মাতা
    0.41
    িমুখে
    0.41
    éristiques
    0.40
     रणबीर
    0.40
     chiedere
    0.40
    栦
    0.40
    न्देल
    0.39
    ὺ
    0.39
    POSITIVE LOGITS
    С
    0.46
    <strong>
    0.43
    ↵
    0.41
     сла
    0.41
    Ста
    0.41
     ఉన్న
    0.41
    服務
    0.41
    Sl
    0.40
    buds
    0.40
    ഠ
    0.40
    Activations Density 0.002%

    No Known Activations