© 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. 10342
    Prev
    Next
    INDEX
    Explanations

    PB followed by SC or MC

    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
    ↵
    -2.94
     thier
    -2.50
    ’:
    -2.50
    </h3>
    -2.44
    al
    -2.39
    <em>
    -2.38
    鸸
    -2.31
     solch
    -2.30
    ,’
    -2.28
    </strong>
    -2.27
    POSITIVE LOGITS
    机的
    2.61
    ability
    2.44
     armée
    2.30
    锘
    2.30
     maît
    2.20
     gloire
    2.17
     saveur
    2.17
    s
    2.17
    　　-
    2.16
     櫃
    2.14
    Activations Density 0.004%

    No Known Activations