© 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. 6292
    Prev
    Next
    INDEX
    Explanations

    HIV and related diseases

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

    create video tutorials

    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
     "^
    0.45
     BUILDING
    0.42
     included
    0.41
     комби
    0.40
    rotl
    0.39
     "#
    0.39
    included
    0.39
     bygg
    0.38
    ,%
    0.38
     "\\
    0.38
    POSITIVE LOGITS
    毆
    0.40
     auxiliar
    0.38
    ğlu
    0.36
    Uz
    0.36
    dets
    0.36
    Tonel
    0.36
    онів
    0.35
     سوری
    0.35
    Approach
    0.35
     APS
    0.35
    Activations Density 0.000%

    No Known Activations