© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 252
    Prev
    Next
    INDEX
    Explanations

    fence, fencing, fenced

    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
    彣
    -3.25
    The
    -3.09
    ”
    -2.78
    甡
    -2.64
    नलोड
    -2.48
    From
    -2.48
    In
    -2.42
    幃
    -2.39
     –
    -2.38
    翼翼
    -2.38
    POSITIVE LOGITS
    崀
    3.14
    <bos>
    2.39
    )
    2.33
     efectivos
    2.28
     conocidas
    2.25
     invitar
    2.25
    不论
    2.22
     preocupar
    2.20
    茕
    2.20
    王的
    2.19
    Activations Density 0.005%

    No Known Activations