© 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. 212571
    Prev
    Next
    INDEX
    Explanations

    announced financial results

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

    Resident Evil franchise

    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
    धीरे
    0.42
    的话
    0.40
    ஃ
    0.40
    }^{*}(
    0.39
     धीरे
    0.38
    endidikan
    0.38
    жется
    0.38
    шали
    0.37
    гро
    0.36
     वगैर
    0.35
    POSITIVE LOGITS
    動画
    0.50
    ě
    0.45
     plastique
    0.44
     verificare
    0.43
    𓇼
    0.43
     영상
    0.43
     Fisch
    0.43
     Revit
    0.42
    尴
    0.42
     কম্পিউ
    0.41
    Activations Density 0.000%

    No Known Activations