© 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. 55205
    Prev
    Next
    INDEX
    Explanations

    adjectives and conjunctions, or sequential actions

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

    intended meaning

    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
     و
    0.47
     افس
    0.45
     sawa
    0.45
    guides
    0.44
     saill
    0.43
     دوس
    0.43
     ਵ
    0.43
    ীব্র
    0.42
     embers
    0.42
    果然
    0.42
    POSITIVE LOGITS
     Decorative
    0.51
    窅
    0.51
     Está
    0.50
     Carefully
    0.47
     Bicycle
    0.46
     Structures
    0.46
     Recall
    0.46
     Watershed
    0.45
    cate
    0.44
     Whenever
    0.44
    Activations Density 0.000%

    No Known Activations