© 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. 105318
    Prev
    Next
    INDEX
    Explanations

    "Retiarius" or similar, argument

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

    argumentation and abstract concepts

    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
     Taiwan
    0.48
    育成
    0.46
    繕
    0.45
    рования
    0.44
    蒎
    0.43
     Colombian
    0.43
    認知
    0.43
    getPackageName
    0.43
    親
    0.42
    arev
    0.42
    POSITIVE LOGITS
     argu
    0.54
     hooded
    0.49
     مقدم
    0.47
     reads
    0.47
     bows
    0.45
     argues
    0.45
    hood
    0.44
     argue
    0.44
     несмотря
    0.44
    jski
    0.43
    Activations Density 0.000%

    No Known Activations