© 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. 27723
    Prev
    Next
    INDEX
    Explanations

    kernel computations

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

    reputational damage

    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
     Rihanna
    0.52
     compañías
    0.47
    💋
    0.46
     Instagram
    0.46
     Sheraton
    0.46
     न्यूयॉर्क
    0.45
     Mardi
    0.45
    💃
    0.45
     Adidas
    0.44
     Flamengo
    0.44
    POSITIVE LOGITS
    >∈</
    0.52
    Binary
    0.50
    Kernel
    0.48
    }=\
    0.46
    Cone
    0.45
    Nodes
    0.45
    })=\
    0.45
     boundedness
    0.45
    Bounded
    0.44
    Polynomial
    0.44
    Activations Density 0.000%

    No Known Activations