© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60184
    Prev
    Next
    INDEX
    Explanations

    tinnitus, non-English words, emojis

    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
     It
    -3.30
    ൎ
    -2.95
    ”،
    -2.59
    تیجه
    -2.56
    sibilidade
    -2.55
    廋
    -2.48
    咨
    -2.42
     ähnliche
    -2.39
    .''
    -2.38
    </sup>
    -2.36
    POSITIVE LOGITS
    
    3.08
    蹌
    2.52
     наших
    2.50
    嘡
    2.39
    {
    2.34
    indelijk
    2.31
    琿
    2.28
    鶿
    2.22
    懸命
    2.20
    峮
    2.17
    Activations Density 0.005%

    No Known Activations