© 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. 128811
    Prev
    Next
    INDEX
    Explanations

    Stat followed by specific words

    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
    h
    -2.45
    </h2>
    -2.45
    媄
    -2.27
    简称
    -2.14
    勍
    -2.11
    哪些
    -2.08
    tdessen
    -2.05
    灕
    -2.03
    唻
    -2.03
    亟
    -1.98
    POSITIVE LOGITS
    ”
    2.77
     рекомендуется
    2.63
    廰
    2.34
     builds
    2.27
    S
    2.20
    そういえば
    2.20
    ～」
    2.14
    粜
    2.13
    “
    2.09
    
    2.08
    Activations Density 0.021%

    No Known Activations