© 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. 74082
    Prev
    Next
    INDEX
    Explanations

    key factors

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

    control or Serpent's Maw

    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
    δες
    0.54
    ндо
    0.54
    नुसार
    0.51
    kook
    0.51
    诚
    0.48
    то
    0.47
     উচ্ছ
    0.46
    де
    0.46
     дворе
    0.45
    لل
    0.45
    POSITIVE LOGITS
    ani
    0.58
     bh
    0.52
     bee
    0.51
     RECEIPTS
    0.47
    ad
    0.46
     src
    0.46
    vil
    0.46
     oil
    0.45
    ">=
    0.45
    veni
    0.45
    Activations Density 0.000%

    No Known Activations