© 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. 22-GEMMASCOPE-RES-131K
    4. 39978
    Prev
    Next
    INDEX
    Explanations

    "Experimental studies"

    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_22/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
    líben
    -1.01
    ゴリー
    -0.94
    umblr
    -0.92
     Dumnezeu
    -0.90
     natuurlijk
    -0.89
     Điện
    -0.88
    側から
    -0.88
    看来
    -0.88
     genug
    -0.85
    為に
    -0.85
    POSITIVE LOGITS
    Partie
    1.05
    ')}}
    0.96
    TWO
    0.95
     незавер
    0.95
    Interes
    0.93
    )$
    0.92
    처럼
    0.91
    THERE
    0.91
    lementary
    0.90
    Turismo
    0.90
    Activations Density 0.000%

    No Known Activations