© 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. 186502
    Prev
    Next
    INDEX
    Explanations

    metal proof career during

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

    ownership of, size of, wait for, parent of

    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
    ア
    0.43
    動力
    0.43
    ा
    0.41
     competent
    0.41
     stup
    0.40
    ソフト
    0.40
    hide
    0.40
     formidable
    0.40
     ice
    0.40
     Möbius
    0.39
    POSITIVE LOGITS
     +=
    0.48
    кай
    0.47
    ServiceImpl
    0.46
    Vacancy
    0.46
     患者
    0.46
    嘬
    0.45
    Malloc
    0.45
    罍
    0.45
     বরাদ্দ
    0.44
     mumbai
    0.44
    Activations Density 0.028%

    No Known Activations