© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15154
    Prev
    Next
    INDEX
    Explanations

    affirmation and reaffirmation

    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
    蟥
    -2.42
    bluza
    -2.23
    眼光
    -2.19
     be
    -2.14
     idealistic
    -2.11
     esos
    -2.11
    AdvEx
    -2.08
     Our
    -2.06
     estos
    -2.03
    ্ড
    -2.03
    POSITIVE LOGITS
    鲵
    2.38
     イラストレーション
    2.30
    ments
    2.11
    喼
    2.08
    鹟
    2.02
    was
    2.02
    ︕
    2.02
    ―――
    1.99
    “
    1.99
    k
    1.97
    Activations Density 0.003%

    No Known Activations