© 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. 104063
    Prev
    Next
    INDEX
    Explanations

    if clause starter

    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
     the
    -1.97
    César
    -1.72
    ጤ
    -1.63
     วาด
    -1.56
     駅前
    -1.55
     編み
    -1.54
     cherchés
    -1.54
    Suka
    -1.52
    Iya
    -1.51
    yoruz
    -1.50
    POSITIVE LOGITS
     If
    1.64
    </b>
    1.55
     "/
    1.53
    ActionCreators
    1.52
     ____
    1.48
     "(
    1.47
     "-
    1.45
     😍
    1.45
     Id
    1.45
    <i>
    1.45
    Activations Density 0.046%

    No Known Activations