© 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. 161668
    Prev
    Next
    INDEX
    Explanations

    Parent Access education forms

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

    embedding hidden

    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
    其他
    0.44
    第一
    0.43
    ვ
    0.42
    怨
    0.42
    src
    0.40
    第
    0.40
    部
    0.39
     شد
    0.39
    ಗು
    0.39
    宗旨
    0.39
    POSITIVE LOGITS
    𝘀
    0.55
     réfrig
    0.54
    printDialog
    0.53
    ोदर
    0.53
     รับ
    0.50
     túi
    0.50
    𝗺
    0.49
    펩
    0.49
     korzyst
    0.49
     pakai
    0.48
    Activations Density 0.000%

    No Known Activations