© 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. 52815
    Prev
    Next
    INDEX
    Explanations

    flow representation

    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
    ocytes
    0.51
    otiv
    0.51
     neutrophils
    0.47
     fibrils
    0.47
    </h3>
    0.46
     ശരീ
    0.46
     bleach
    0.46
    moi
    0.46
     fermions
    0.45
     Oils
    0.45
    POSITIVE LOGITS
    ERE
    0.43
    listdir
    0.43
    httphttps
    0.42
    دارة
    0.42
    嚧
    0.42
     KELL
    0.41
    ڑا
    0.40
    摈
    0.40
     Quelle
    0.39
     போக்குவர
    0.39
    Activations Density 0.002%

    No Known Activations