© 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-65K
    4. 8653
    Prev
    Next
    INDEX
    Explanations

    however, then snap

    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_65k_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
    䍘
    0.45
    湋
    0.42
     Taille
    0.42
     Sergei
    0.41
     Artwork
    0.41
     Lúc
    0.41
    വൃ
    0.40
     televiz
    0.39
     Сергея
    0.38
    竑
    0.38
    POSITIVE LOGITS
    aw
    0.44
    core
    0.43
     institutes
    0.42
    api
    0.42
    utils
    0.42
    _
    0.42
    ew
    0.41
    oy
    0.41
    crm
    0.41
    io
    0.41
    Activations Density 0.008%

    No Known Activations