© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52492
    Prev
    Next
    INDEX
    Explanations

    languages other than English

    np_acts-logits-general · gemini-2.5-flash-lite

    describing descriptive adjectives and their context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daughters
    0.49
     rectum
    0.49
     Les
    0.48
     vs
    0.48
     N
    0.47
    yn
    0.46
     reductase
    0.46
     inch
    0.46
     Conventions
    0.46
     mencionados
    0.46
    POSITIVE LOGITS
    给
    0.61
    盐
    0.55
     정보를
    0.54
    甚至
    0.51
    处理器
    0.51
    能够
    0.50
    菜单
    0.50
    甚至是
    0.50
    Чтобы
    0.49
    给我们
    0.49
    Activations Density 0.000%

    No Known Activations