© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56862
    Prev
    Next
    INDEX
    Explanations

    registrations, reservations, decided, builds

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

    financial terms and indicators

    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
     IV
    0.47
    章
    0.46
    r
    0.46
    ння
    0.43
    見
    0.42
     American
    0.42
     アメリカ
    0.42
    >
    0.41
     அதே
    0.41
    ۩
    0.41
    POSITIVE LOGITS
     Rage
    0.54
    Trading
    0.53
    Shipping
    0.53
     Yachts
    0.52
    Entertainment
    0.52
    Loved
    0.52
    लो
    0.51
     Shipping
    0.51
    tableLayoutPanel
    0.51
    RE
    0.50
    Activations Density 0.000%

    No Known Activations