© 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. 5896
    Prev
    Next
    INDEX
    Explanations

    protects surfaces

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

    surfaces and components

    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
     квали
    0.51
    غول
    0.45
     охорони
    0.45
     množ
    0.44
     रेत
    0.44
     योग्यता
    0.44
     божомолдор
    0.44
    蓣
    0.44
     왼
    0.43
     विशाल
    0.42
    POSITIVE LOGITS
     surfaces
    1.93
     Surfaces
    1.52
     поверхности
    1.34
     crevices
    1.30
     joints
    1.15
     seams
    1.15
     superficies
    1.13
     edges
    1.09
     exposed
    1.09
     interiors
    0.98
    Activations Density 0.247%

    No Known Activations