© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136107
    Prev
    Next
    INDEX
    Explanations

    hosting, value, building, name, UI

    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
    iritual
    0.49
    琐
    0.48
     ह
    0.45
    𝙍
    0.44
    ស្រាយ
    0.44
     constantes
    0.43
    eti
    0.42
    徊
    0.42
     تع
    0.42
    ्राफी
    0.41
    POSITIVE LOGITS
     axles
    0.49
    檛
    0.47
    エコ
    0.46
    я
    0.46
     environmentally
    0.45
    동산
    0.45
     TCM
    0.45
     Macs
    0.45
    мый
    0.44
    әп
    0.44
    Activations Density 0.001%

    No Known Activations