© 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. 102603
    Prev
    Next
    INDEX
    Explanations

    offering Him, island, standards, eventually Maddox, spent many, mere biological

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

    micro-entrepreneurship and neighborly help

    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
    ногие
    0.54
    новый
    0.49
    Adidas
    0.48
    াব্দ
    0.47
    чь
    0.47
    
    0.47
    كيد
    0.46
    Ꮇ
    0.46
    нос
    0.45
     चैप्टर्स
    0.45
    POSITIVE LOGITS
    is
    0.50
    jid
    0.50
    are
    0.49
     kül
    0.49
    use
    0.48
     j
    0.48
     kesk
    0.47
    ಳು
    0.47
    ji
    0.47
     Villanueva
    0.45
    Activations Density 0.001%

    No Known Activations