© 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. 197913
    Prev
    Next
    INDEX
    Explanations

    structured settlement funding

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

    implicit explanations

    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
    ᚨ
    0.47
     था
    0.46
    ফ
    0.44
     ještě
    0.44
    하여
    0.44
     estancia
    0.43
    ൨
    0.43
    ্ভ
    0.43
     nails
    0.43
    וא
    0.42
    POSITIVE LOGITS
    olicy
    0.50
    ្នក
    0.47
    on
    0.47
    wrapper
    0.46
    muted
    0.45
    impl
    0.44
    implicitly
    0.43
     morally
    0.43
    sciences
    0.43
    ScrollView
    0.42
    Activations Density 0.000%

    No Known Activations