© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 260
    Prev
    Next
    INDEX
    Explanations

    error causes and details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </u>
    -1.45
    rightarrow
    -1.44
     was
    -1.43
     its
    -1.33
     who
    -1.33
     to
    -1.24
    го
    -1.23
    -£
    -1.21
    ⁛
    -1.20
    ↵↵
    -1.17
    POSITIVE LOGITS
    還可以
    1.38
    Они
    1.33
    Demikian
    1.27
    alties
    1.26
    logías
    1.23
    除此之外
    1.23
    Several
    1.22
    Neither
    1.22
     borracha
    1.20
    いかがでしたか
    1.20
    Activations Density 0.048%

    No Known Activations