© 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. 29502
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
     discovering
    0.43
    thanks
    0.42
    research
    0.42
     छात्रा
    0.42
    rows
    0.41
    树
    0.40
    绿色
    0.40
    ac
    0.39
    color
    0.39
    eigen
    0.39
    POSITIVE LOGITS
    濋
    0.49
     Италии
    0.43
     italiane
    0.43
     Norge
    0.42
     ఎన్నిక
    0.42
     dnes
    0.41
    ക്കാല
    0.41
     Belgien
    0.40
    ChooseServer
    0.40
     negó
    0.40
    Activations Density 0.001%

    No Known Activations