© 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. 172561
    Prev
    Next
    INDEX
    Explanations

    being cannot

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

    exploring consequences of societal systems

    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
    ントン
    0.43
     intervalles
    0.40
    িয়াম
    0.40
     giorni
    0.39
    加え
    0.39
     চারপাশে
    0.39
    ]//
    0.39
    ज़ा
    0.39
     REN
    0.39
    anjan
    0.38
    POSITIVE LOGITS
     tete
    0.48
    理念
    0.48
    Menus
    0.47
    Motivation
    0.46
    心理
    0.46
    窍
    0.45
    著作
    0.45
    Pune
    0.44
    Drinking
    0.44
     lezione
    0.44
    Activations Density 0.000%

    No Known Activations