© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 104387
    Prev
    Next
    INDEX
    Explanations

    product

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

    actions and outcomes

    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
    烺
    0.47
    铀
    0.46
     kullanım
    0.46
    ıştı
    0.45
     önem
    0.43
     питання
    0.43
     hükü
    0.43
     használ
    0.43
     расположены
    0.43
    壳
    0.43
    POSITIVE LOGITS
     lax
    0.52
    mia
    0.51
    ep
    0.49
    quel
    0.49
    ilo
    0.48
     wreaths
    0.48
    ੀ
    0.47
     Gand
    0.47
    slow
    0.46
     would
    0.46
    Activations Density 0.001%

    No Known Activations