© 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. 78948
    Prev
    Next
    INDEX
    Explanations

    Recombinant Proteins/Terminated Management/White Hat SEO

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

    Domain, node, parameters, intensity, inference

    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
    <unused709>
    0.45
     heartfelt
    0.44
    <unused558>
    0.43
    <unused983>
    0.43
     nuanced
    0.43
     quatro
    0.43
    <unused2007>
    0.42
     diez
    0.42
     heutigen
    0.42
     gustó
    0.42
    POSITIVE LOGITS
    Types
    0.43
     normalerweise
    0.43
    是一种
    0.43
    是一個
    0.42
    ＝
    0.42
    视图
    0.41
    θ
    0.41
    是一種
    0.41
     types
    0.41
    "=
    0.41
    Activations Density 0.018%

    No Known Activations