© 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. 133972
    Prev
    Next
    INDEX
    Explanations

    ceiling hoist and tooth case

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

    largest eyes, IQ tests

    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
    یز
    0.50
    ین
    0.50
     permissive
    0.48
    ДК
    0.47
    א
    0.46
     manière
    0.46
    סטי
    0.46
    מר
    0.45
    ک
    0.45
    𝔹
    0.45
    POSITIVE LOGITS
    擔心
    0.48
     دوبارہ
    0.46
     왜
    0.45
     बाजारों
    0.45
    會有
    0.45
     Kiểm
    0.44
    媽媽
    0.43
     그렇게
    0.43
     گھ
    0.42
     guards
    0.41
    Activations Density 0.001%

    No Known Activations