© 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. 84532
    Prev
    Next
    INDEX
    Explanations

    items, products, facts, topics

    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
     tantangan
    -1.47
     حتی
    -1.44
    *-*-
    -1.43
     with
    -1.37
     kesempatan
    -1.36
     conjunction
    -1.34
    鱘
    -1.32
    要说
    -1.27
    昞
    -1.25
    aquin
    -1.24
    POSITIVE LOGITS
    おわりに
    1.80
    Still
    1.79
    still
    1.74
     applaud
    1.69
     ITEMS
    1.65
    They
    1.59
    婭
    1.55
    Again
    1.53
    CHREIB
    1.52
    ⵌ
    1.48
    Activations Density 0.000%

    No Known Activations