© 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. 12815
    Prev
    Next
    INDEX
    Explanations

    a followed by roles or entities

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

    a followed by a descriptor

    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
     -"
    0.46
     $"
    0.45
     asserting
    0.44
    --"
    0.44
     heps
    0.44
     "`
    0.44
     ")
    0.43
     ["
    0.43
     ជា
    0.42
     [%
    0.42
    POSITIVE LOGITS
     ktorí
    0.41
     précédemment
    0.41
     ehemaligen
    0.40
     которых
    0.39
    らが
    0.39
    公子
    0.39
    ви
    0.38
     मशहूर
    0.38
    খ্যাত
    0.38
    вите
    0.38
    Activations Density 0.050%

    No Known Activations