© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3780
    Prev
    Next
    INDEX
    Explanations

    locations and services

    np_acts-logits-general · gemini-2.5-flash-lite

    specification or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    完整的
    0.47
     Radiological
    0.47
    三個
    0.44
    ActionEvent
    0.42
    蕗
    0.42
    に対して
    0.40
    截至
    0.40
    GISLATIVE
    0.40
    特殊的
    0.39
    }^{
    0.39
    POSITIVE LOGITS
     nyc
    0.92
     malaysia
    0.91
     dubai
    0.89
     singapore
    0.88
     Cheap
    0.86
    Cheap
    0.84
     canada
    0.83
     cheap
    0.82
     kaufen
    0.81
     купить
    0.80
    Activations Density 1.342%

    No Known Activations