© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 141161
    Prev
    Next
    INDEX
    Explanations

    in support of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }
    0.81
    n
    0.71
    )
    0.70
     N
    0.68
    ")
    0.67
    ر
    0.66
     on
    0.65
    re
    0.65
    Name
    0.65
    De
    0.64
    POSITIVE LOGITS
     reluctantly
    0.66
    bbero
    0.66
     кожного
    0.66
     resisting
    0.65
    idiendo
    0.64
    carrito
    0.64
    ட்டும்
    0.64
    чиго
    0.64
    a
    0.64
     качестве
    0.63
    Activations Density 0.003%

    No Known Activations