© 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. 104810
    Prev
    Next
    INDEX
    Explanations

    loading or unloading items and vehicles

    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
    Perhaps
    -2.13
    Does
    -2.06
    Other
    -2.06
     ketika
    -2.05
    when
    -2.02
    What
    -1.98
    ますが
    -1.95
    März
    -1.95
    ly
    -1.94
    Why
    -1.92
    POSITIVE LOGITS
    ]
    2.52
    鴆
    2.27
    ates
    2.25
    ︲
    2.17
    狴
    2.17
    ꯷
    2.16
    蚡
    2.13
    歺
    2.05
    diseases
    2.05
    鶿
    2.02
    Activations Density 0.002%

    No Known Activations