© 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. 112730
    Prev
    Next
    INDEX
    Explanations

    colleges, water, effect, prices, moat, Union, actions

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

    res followed by comma

    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
    素敵
    0.43
    迷
    0.42
    誤
    0.40
    )});
    0.40
    lyn
    0.39
    旖
    0.39
     esclare
    0.39
    疑問
    0.38
    ḧ
    0.38
    ไลน์
    0.38
    POSITIVE LOGITS
     alumina
    0.44
    MakeRect
    0.43
     tableware
    0.43
    PlatformTarget
    0.43
    quela
    0.42
     inaction
    0.42
     tubers
    0.41
     casks
    0.41
     Та
    0.40
    لە
    0.40
    Activations Density 0.000%

    No Known Activations