© 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. 295
    Prev
    Next
    INDEX
    Explanations

    describing how something is done

    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
    鋱
    -2.75
    ﹆
    -2.73
    aktionen
    -2.61
     alojamientos
    -2.59
    dáms
    -2.59
     ruinas
    -2.59
     みた
    -2.53
    tentu
    -2.45
     profondo
    -2.42
    熺
    -2.42
    POSITIVE LOGITS
    <td>
    3.31
    .
    3.30
    This
    2.64
    ка
    2.55
    <em>
    2.53
     Many
    2.52
    re
    2.42
    是被
    2.39
     From
    2.36
    on
    2.30
    Activations Density 0.004%

    No Known Activations