© 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. 196809
    Prev
    Next
    INDEX
    Explanations

    always wanted

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

    high energy density, distance, eternity

    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
     Nested
    0.51
    أة
    0.50
    繁
    0.47
    地方
    0.46
     lateinit
    0.44
    鞍
    0.44
    اط
    0.44
    自身
    0.44
    。
    0.43
    饮
    0.43
    POSITIVE LOGITS
    លេ
    0.58
    ordine
    0.58
     удовле
    0.55
    lar
    0.53
     мощности
    0.53
    rela
    0.52
    um
    0.52
    ry
    0.52
     космети
    0.52
     buat
    0.51
    Activations Density 0.000%

    No Known Activations